kubernetes
/
website
mirror of https://github.com/kubernetes/website.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

cpumanager: document cpu manager static policy options 

The enhancement https://github.com/kubernetes/enhancements/issues/2625
want to add a new kubelet option to fine tune the behaviour of the
cpu manager policies, and to do so we add support for cpu manager policy
options themselves.

Signed-off-by: Francesco Romani <fromani@redhat.com>
pull/27891/head
Francesco Romani 2021-05-06 11:57:08 +02:00
parent 61047b9fa9
commit a376a29d7e
2 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
content/en/docs/reference/command-line-tools-reference/kubelet.md
View File

@ -277,6 +277,13 @@ kubelet [flags]
<td></td><td style="line-height: 130%; word-wrap: break-word;">CPU Manager policy to use. Possible values: `none`, `static`. (DEPRECATED: This parameter should be set via the config file specified by the Kubelet's `--config` flag. See https://kubernetes.io/docs/tasks/administer-cluster/kubelet-config-file/ for more information.)</td>
</tr>
<tr>
<td colspan="2">--cpu-manager-policy-options strings</td>
</tr>
<tr>
<td></td><td style="line-height: 130%; word-wrap: break-word;">Comma-separated list of options to fine-tune the behavior of the CPU Manager policy to use. (DEPRECATED: This parameter should be set via the config file specified by the Kubelet's `--config` flag. See https://kubernetes.io/docs/tasks/administer-cluster/kubelet-config-file/ for more information.)</td>
</tr>
<tr>
<td colspan="2">--cpu-manager-reconcile-period duration&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Default: `10s`</td>
</tr>

13
content/en/docs/tasks/administer-cluster/cpu-management-policies.md
View File

@ -58,6 +58,9 @@ frequency is set through a new Kubelet configuration value
`--cpu-manager-reconcile-period`. If not specified, it defaults to the same
duration as `--node-status-update-frequency`.
The behavior of the static policy can be fine-tuned using the `--cpu-manager-policy-options` flag.
The flag takes a comma-separated list of `key=value` policy options.
### None policy
The `none` policy explicitly enables the existing default CPU
@ -212,4 +215,14 @@ and `requests` are set equal to `limits` when not explicitly specified. And the
container's resource limit for the CPU resource is an integer greater than or
equal to one. The `nginx` container is granted 2 exclusive CPUs.
#### Static policy options
If the `full-pcpus-only` policy option is specified, the static policy will always allocate full physical cores.
You can enable this option by adding `full-pcups-only=true` to the CPUManager policy options.
By default, without this option, the static policy allocates CPUs using a topology-aware best-fit allocation.
On SMT enabled systems, the policy can allocate individual virtual cores, which correspond to hardware threads.
This can lead to different containers sharing the same physical cores; this behaviour in turn contributes
to the [noisy neighbours problem](https://en.wikipedia.org/wiki/Cloud_computing_issues#Performance_interference_and_noisy_neighbors).
With the option enabled, the pod will be admitted by the kubelet only if the CPU request of all its containers
can be fulfilled by allocating full physical cores.
If the pod does not pass the admission, it will be put in Failed state with the message `SMTAlignmentError`.