//   have observed 12 micros on 64-bit linux systems to wake up a parked thread). So if the
  //   timeout is small we shouldn't park(). This needs to be traded off with the cpu overhead of
  //   spinning, so we use SPIN_THRESHOLD_NANOS which is what AbstractQueuedSynchronizer uses for
  //   similar purposes.
  // * We want to behave reasonably for timeouts of 0

  //   have observed 12 micros on 64-bit linux systems to wake up a parked thread). So if the
  //   timeout is small we shouldn't park(). This needs to be traded off with the cpu overhead of
  //   spinning, so we use SPIN_THRESHOLD_NANOS which is what AbstractQueuedSynchronizer uses for
  //   similar purposes.
  // * We want to behave reasonably for timeouts of 0

 * either of these extremes, {@code Striped} allows the user to trade between required concurrency
 * and memory footprint. For example, if a set of tasks are CPU-bound, one could easily create a
 * very compact {@code Striped<Lock>} of {@code availableProcessors() * 4} stripes, instead of
 * possibly thousands of locks which could be created in a {@code Map<K, Lock>} structure.
 *

Безусловно, на этом же сервере будут работать и **другие процессы**, которые не относятся к вашему приложению.

Интересная деталь заключается в том, что процент **использования центрального процессора (CPU)** каждым процессом может сильно меняться с течением времени, но объём занимаемой **оперативной памяти (RAM)** остаётся относительно **стабильным**.

          "interval": "",
          "legendFormat": "{{server}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "CPU Usage",
      "type": "gauge"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },

- Fixed relative CPU priority for pods where containers explicitly request zero cpu by giving the lowest priority instead of falling back to the cpu limit to avoid possible cpu starvation of other pods. ([#108832](https://github.com/kubernetes/kubernetes/pull/108832), [@waynepeking348](https://github.com/waynepeking348))

- Added support for `--cpu`, `--memory` flag to `kubectl autoscale`, started deprecating `--cpu-precent`. ([#129373](https://github.com/kubernetes/kubernetes/pull/129373), [@googs1025](https://github.com/googs1025))

  * Create clusters with GPUs in GCE by specifying `type=<gpu-type>,count=<gpu-count>` to NODE_ACCELERATORS environment variable. ([#45130](https://github.com/kubernetes/kubernetes/pull/45130), [@vishh](https://github.com/vishh))

    * List of available GPUs - [https://cloud.google.com/compute/docs/gpus/#introduction](https://cloud.google.com/compute/docs/gpus/#introduction)

making compression the default for everyone starting with this release candidate.

Please be considerate of your servers and their operators as you roll out this release. Compression
saves bandwidth but it costs CPU and memory! If you run into a problem you may need to adjust or
disable the `permessage-deflate` compression settings on your server.

Note that OkHttp won't use compression when sending messages smaller than 1 KiB.

* Fix the DOCKER_OPTS appending bug. ([#33163](https://github.com/kubernetes/kubernetes/pull/33163), [@DjangoPeng](https://github.com/DjangoPeng))
* Remove cpu limits for dns pod to avoid CPU starvation ([#33227](https://github.com/kubernetes/kubernetes/pull/33227), [@vishh](https://github.com/vishh))