Compare commits

..

3 Commits

Author SHA1 Message Date
Fupan Li
c376ab5de7 runtime-rs: fix the issue of hot-unplug memory smaller
It should do nothing instead of return an error when
hot-unplug the memory to the size smaller than static
plugged memory size.

Signed-off-by: Fupan Li <fupan.lfp@antgroup.com>
2025-11-10 14:17:44 +08:00
Fupan Li
200abc815c tests: fix the issue of missing teardown pods
Signed-off-by: Fupan Li <fupan.lfp@antgroup.com>
2025-11-10 10:30:17 +08:00
Fupan Li
333d12dc47 runtime: fix the issue of update interface error
Since the network device hotplug is an asynchronous operation,
it's possible that the hotplug operation had returned, but
the network device hasn't ready in guest, thus it's better to
retry on this operation to wait until the device ready in guest.

Signed-off-by: Fupan Li <fupan.lfp@antgroup.com>
2025-11-07 11:29:57 +08:00
1649 changed files with 46522 additions and 107450 deletions

View File

@@ -1,37 +0,0 @@
# yaml-language-server: $schema=https://raw.githubusercontent.com/streetsidesoftware/cspell/main/cspell.schema.json
version: "0.2"
language: en,en-GB
dictionaryDefinitions:
- name: kata-terms
path: ./tests/spellcheck/kata-dictionary.txt
addWords: true
dictionaries:
- en-GB
- en_US
- bash
- git
- golang
- k8s
- python
- rust
- companies
- mnemonics
- peopleNames
- softwareTerms
- networking-terms
- kata-terms
ignoreRegExpList:
- /@[a-z\d](?:[a-z\d]|-(?=[a-z\d])){0,38}/gi # Ignores github handles
# Ignore code blocks
- /^\s*`{3,}[\s\S]*?^\s*`{3,}/gm
- /`[^`\n]+`/g
ignorePaths:
- "**/vendor/**" # vendor files aren't owned by us
- "**/src/runtime/virtcontainers/pkg/cloud-hypervisor/client/**" # Generated files
- "**/requirements.txt"
useGitignore: true

View File

@@ -1,7 +0,0 @@
root = true
[*]
charset = utf-8
end_of_line = lf
insert_final_newline = true
trim_trailing_whitespace = true

View File

@@ -1,30 +0,0 @@
{
"Verbose": false,
"Debug": false,
"IgnoreDefaults": false,
"SpacesAfterTabs": false,
"NoColor": false,
"Exclude": [
"src/runtime/vendor",
"src/tools/log-parser/vendor",
"tests/metrics/cmd/checkmetrics/vendor",
"tests/vendor",
"src/runtime/virtcontainers/pkg/cloud-hypervisor/client",
"\\.img$",
"\\.dtb$",
"\\.drawio$",
"\\.svg$",
"\\.patch$"
],
"AllowedContentTypes": [],
"PassedFiles": [],
"Disable": {
"EndOfLine": false,
"Indentation": false,
"IndentSize": false,
"InsertFinalNewline": false,
"TrimTrailingWhitespace": false,
"MaxLineLength": false,
"Charset": false
}
}

View File

@@ -10,6 +10,11 @@ self-hosted-runner:
- amd64-nvidia-a100
- amd64-nvidia-h100-snp
- arm64-k8s
- containerd-v1.7-overlayfs
- containerd-v2.0-overlayfs
- containerd-v2.1-overlayfs
- containerd-v2.2
- containerd-v2.2-overlayfs
- garm-ubuntu-2004
- garm-ubuntu-2004-smaller
- garm-ubuntu-2204
@@ -20,17 +25,10 @@ self-hosted-runner:
- ppc64le-k8s
- ppc64le-small
- ubuntu-24.04-ppc64le
- ubuntu-24.04-s390x
- metrics
- riscv-builder
- sev-snp
- s390x
- s390x-large
- tdx
- ubuntu-24.04-arm
paths:
.github/workflows/**/*.{yml,yaml}:
ignore:
# We use if: false to "temporarily" skip jobs with issues
- 'constant expression "false" in condition'
- ubuntu-22.04-arm

View File

@@ -17,7 +17,7 @@ runs:
uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: nightly
toolchain: nightly
override: true
- name: Cache

View File

@@ -12,11 +12,10 @@ updates:
- "/src/tools/agent-ctl"
- "/src/tools/genpolicy"
- "/src/tools/kata-ctl"
- "/src/tools/runk"
- "/src/tools/trace-forwarder"
schedule:
interval: "daily"
cooldown:
default-days: 7
ignore:
# rust-vmm repos might cause incompatibilities on patch versions, so
# lets handle them manually for now.
@@ -37,9 +36,9 @@ updates:
# create groups for common dependencies, so they can all go in a single PR
# We can extend this as we see more frequent groups
groups:
aws-libcrypto:
bit-vec:
patterns:
- aws-lc-*
- bit-vec
bumpalo:
patterns:
- bumpalo
@@ -67,9 +66,6 @@ updates:
rustix:
patterns:
- rustix
rustls-webpki:
patterns:
- rustls-webpki
slab:
patterns:
- slab
@@ -90,12 +86,8 @@ updates:
- "src/tools/csi-kata-directvolume"
schedule:
interval: "daily"
cooldown:
default-days: 7
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "monthly"
cooldown:
default-days: 7

View File

@@ -13,13 +13,18 @@ concurrency:
jobs:
run-actionlint:
name: run-actionlint
env:
GH_TOKEN: ${{ github.token }}
runs-on: ubuntu-24.04
steps:
- name: Checkout the code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
persist-credentials: false
- name: Install actionlint gh extension
run: gh extension install https://github.com/cschleiden/gh-actionlint
- name: Run actionlint
uses: raven-actions/actionlint@e01d1ea33dd6a5ed517d95b4c0c357560ac6f518 # v2.1.1
run: gh actionlint

View File

@@ -47,23 +47,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
- name: Install dependencies
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies
env:
@@ -88,7 +71,7 @@ jobs:
fail-fast: false
matrix:
containerd_version: ['lts', 'active']
vmm: ['clh', 'cloud-hypervisor', 'dragonball', 'qemu', 'qemu-runtime-rs']
vmm: ['clh', 'cloud-hypervisor', 'dragonball', 'qemu']
runs-on: ubuntu-22.04
env:
CONTAINERD_VERSION: ${{ matrix.containerd_version }}
@@ -134,7 +117,7 @@ jobs:
fail-fast: false
matrix:
containerd_version: ['lts', 'active']
vmm: ['clh', 'qemu', 'dragonball', 'qemu-runtime-rs']
vmm: ['clh', 'qemu', 'dragonball']
runs-on: ubuntu-22.04
env:
CONTAINERD_VERSION: ${{ matrix.containerd_version }}
@@ -164,22 +147,49 @@ jobs:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata
run: bash tests/integration/nydus/gha-run.sh install-kata kata-artifacts
- name: Install kata-tools
run: bash tests/integration/nydus/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Run nydus tests
timeout-minutes: 10
run: bash tests/integration/nydus/gha-run.sh run
run-runk:
name: run-runk
# Skip runk tests as we have no maintainers. TODO: Decide when to remove altogether
if: false
runs-on: ubuntu-22.04
env:
CONTAINERD_VERSION: lts
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install dependencies
run: bash tests/integration/runk/gha-run.sh install-dependencies
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata
run: bash tests/integration/runk/gha-run.sh install-kata kata-artifacts
- name: Run runk tests
timeout-minutes: 10
run: bash tests/integration/runk/gha-run.sh run
run-tracing:
name: run-tracing
strategy:
@@ -269,6 +279,50 @@ jobs:
timeout-minutes: 15
run: bash tests/functional/vfio/gha-run.sh run
run-docker-tests:
name: run-docker-tests
strategy:
# We can set this to true whenever we're 100% sure that
# all the tests are not flaky, otherwise we'll fail them
# all due to a single flaky instance.
fail-fast: false
matrix:
vmm:
- qemu
runs-on: ubuntu-22.04
env:
KATA_HYPERVISOR: ${{ matrix.vmm }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install dependencies
run: bash tests/integration/docker/gha-run.sh install-dependencies
env:
GH_TOKEN: ${{ github.token }}
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata
run: bash tests/integration/docker/gha-run.sh install-kata kata-artifacts
- name: Run docker smoke test
timeout-minutes: 5
run: bash tests/integration/docker/gha-run.sh run
run-nerdctl-tests:
name: run-nerdctl-tests
strategy:
@@ -282,7 +336,6 @@ jobs:
- dragonball
- qemu
- cloud-hypervisor
- qemu-runtime-rs
runs-on: ubuntu-22.04
env:
KATA_HYPERVISOR: ${{ matrix.vmm }}
@@ -357,16 +410,8 @@ jobs:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata & kata-tools
run: |
bash tests/functional/kata-agent-apis/gha-run.sh install-kata kata-artifacts
bash tests/functional/kata-agent-apis/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Install kata
run: bash tests/functional/kata-agent-apis/gha-run.sh install-kata kata-artifacts
- name: Run kata agent api tests with agent-ctl
run: bash tests/functional/kata-agent-apis/gha-run.sh run

View File

@@ -47,25 +47,8 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
- name: Install dependencies
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies
run: bash tests/integration/cri-containerd/gha-run.sh
env:
GH_TOKEN: ${{ github.token }}
@@ -123,3 +106,44 @@ jobs:
- name: Run containerd-stability tests
timeout-minutes: 15
run: bash tests/stability/gha-run.sh run
run-docker-tests:
name: run-docker-tests
strategy:
# We can set this to true whenever we're 100% sure that
# all the tests are not flaky, otherwise we'll fail them
# all due to a single flaky instance.
fail-fast: false
matrix:
vmm: ['qemu']
runs-on: s390x-large
env:
KATA_HYPERVISOR: ${{ matrix.vmm }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install dependencies
run: bash tests/integration/docker/gha-run.sh install-dependencies
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-s390x${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata
run: bash tests/integration/docker/gha-run.sh install-kata kata-artifacts
- name: Run docker smoke test
timeout-minutes: 5
run: bash tests/integration/docker/gha-run.sh run

View File

@@ -82,17 +82,11 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
if: contains(matrix.component.needs, 'golang')
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
if: contains(matrix.component.needs, 'golang')
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Setup rust
if: contains(matrix.component.needs, 'rust')
run: |

View File

@@ -12,12 +12,7 @@ name: Build checks
jobs:
check:
name: check
runs-on: >-
${{
( contains(inputs.instance, 's390x') && matrix.component.name == 'runtime' ) && 's390x' ||
( contains(inputs.instance, 'ppc64le') && (matrix.component.name == 'runtime' || matrix.component.name == 'agent') ) && 'ppc64le' ||
inputs.instance
}}
runs-on: ${{ matrix.component.name == 'runtime' && inputs.instance == 'ubuntu-24.04-s390x' && 's390x' || matrix.component.name == 'runtime' && inputs.instance == 'ubuntu-24.04-ppc64le' && 'ppc64le' || inputs.instance }}
strategy:
fail-fast: false
matrix:
@@ -73,8 +68,6 @@ jobs:
needs:
- rust
- protobuf-compiler
instance:
- ${{ inputs.instance }}
steps:
- name: Adjust a permission for repo
@@ -94,19 +87,11 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
if: contains(matrix.component.needs, 'golang')
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
if: contains(matrix.component.needs, 'golang')
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: ${{ contains(inputs.instance, 'ppc64le') && 'ppc64le' || '' }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Setup rust
if: contains(matrix.component.needs, 'rust')
run: |

View File

@@ -41,23 +41,29 @@ jobs:
matrix:
asset:
- agent
- agent-ctl
- busybox
- cloud-hypervisor
- cloud-hypervisor-glibc
- coco-guest-components
- csi-kata-directvolume
- firecracker
- genpolicy
- kata-ctl
- kata-manager
- kernel
- kernel-debug
- kernel-confidential
- kernel-dragonball-experimental
- kernel-nvidia-gpu
- kernel-nvidia-gpu-confidential
- nydus
- ovmf
- ovmf-sev
- ovmf-tdx
- pause-image
- qemu
- qemu-snp-experimental
- qemu-tdx-experimental
- trace-forwarder
- virtiofsd
stage:
- ${{ inputs.stage }}
@@ -115,7 +121,7 @@ jobs:
echo "oci-name=${oci_image%@*}" >> "$GITHUB_OUTPUT"
echo "oci-digest=${oci_image#*@}" >> "$GITHUB_OUTPUT"
- uses: oras-project/setup-oras@22ce207df3b08e061f537244349aac6ae1d214f6 # v1.2.4
- uses: oras-project/setup-oras@5c0b487ce3fe0ce3ab0d034e63669e426e294e4d # v1.2.2
if: ${{ env.PERFORM_ATTESTATION == 'yes' }}
with:
version: "1.2.0"
@@ -147,8 +153,8 @@ jobs:
if: ${{ startsWith(matrix.asset, 'kernel-nvidia-gpu') }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-artifacts-amd64-${{ matrix.asset }}-modules${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}-modules.tar.zst
name: kata-artifacts-amd64-${{ matrix.asset }}-headers${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}-headers.tar.zst
retention-days: 15
if-no-files-found: error
@@ -165,10 +171,10 @@ jobs:
- rootfs-image
- rootfs-image-confidential
- rootfs-image-mariner
- rootfs-image-nvidia-gpu
- rootfs-image-nvidia-gpu-confidential
- rootfs-initrd
- rootfs-initrd-confidential
- rootfs-initrd-nvidia-gpu
- rootfs-initrd-nvidia-gpu-confidential
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
@@ -234,7 +240,8 @@ jobs:
asset:
- busybox
- coco-guest-components
- kernel-nvidia-gpu-modules
- kernel-nvidia-gpu-headers
- kernel-nvidia-gpu-confidential-headers
- pause-image
steps:
- uses: geekyeggo/delete-artifact@f275313e70c08f6120db482d7a6b98377786765b # v5.1.0
@@ -348,16 +355,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
@@ -365,113 +362,3 @@ jobs:
path: kata-static.tar.zst
retention-days: 15
if-no-files-found: error
build-tools-asset:
name: build-tools-asset
runs-on: ubuntu-22.04
permissions:
contents: read
packages: write
strategy:
matrix:
asset:
- agent-ctl
- genpolicy
- kata-ctl
- kata-manager
- trace-forwarder
stage:
- ${{ inputs.stage }}
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: quay.io
username: ${{ vars.QUAY_DEPLOYER_USERNAME }}
password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0 # This is needed in order to keep the commit ids history
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Build ${{ matrix.asset }}
id: build
run: |
make "${KATA_ASSET}-tarball"
build_dir=$(readlink -f build)
# store-artifact does not work with symlink
mkdir -p kata-tools-build && cp "${build_dir}"/kata-static-"${KATA_ASSET}"*.tar.* kata-tools-build/.
env:
KATA_ASSET: ${{ matrix.asset }}
TAR_OUTPUT: ${{ matrix.asset }}.tar.gz
PUSH_TO_REGISTRY: ${{ inputs.push-to-registry }}
ARTEFACT_REGISTRY: ghcr.io
ARTEFACT_REGISTRY_USERNAME: ${{ github.actor }}
ARTEFACT_REGISTRY_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
TARGET_BRANCH: ${{ inputs.target-branch }}
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: store-artifact ${{ matrix.asset }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-tools-artifacts-amd64-${{ matrix.asset }}${{ inputs.tarball-suffix }}
path: kata-tools-build/kata-static-${{ matrix.asset }}.tar.zst
retention-days: 15
if-no-files-found: error
create-kata-tools-tarball:
name: create-kata-tools-tarball
runs-on: ubuntu-22.04
needs: [build-tools-asset]
permissions:
contents: read
packages: write
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
fetch-tags: true
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-artifacts
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
pattern: kata-tools-artifacts-amd64-*${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
merge-multiple: true
- name: merge-artifacts
run: |
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-tools-artifacts versions.yaml kata-tools-static.tar.zst
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata-tools tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-tools-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-static.tar.zst
retention-days: 15
if-no-files-found: error

View File

@@ -31,7 +31,7 @@ permissions: {}
jobs:
build-asset:
name: build-asset
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
permissions:
contents: read
packages: write
@@ -45,7 +45,6 @@ jobs:
- cloud-hypervisor
- firecracker
- kernel
- kernel-debug
- kernel-dragonball-experimental
- kernel-nvidia-gpu
- kernel-cca-confidential
@@ -103,7 +102,7 @@ jobs:
echo "oci-name=${oci_image%@*}" >> "$GITHUB_OUTPUT"
echo "oci-digest=${oci_image#*@}" >> "$GITHUB_OUTPUT"
- uses: oras-project/setup-oras@22ce207df3b08e061f537244349aac6ae1d214f6 # v1.2.4
- uses: oras-project/setup-oras@5c0b487ce3fe0ce3ab0d034e63669e426e294e4d # v1.2.2
if: ${{ env.PERFORM_ATTESTATION == 'yes' }}
with:
version: "1.2.0"
@@ -135,14 +134,14 @@ jobs:
if: ${{ startsWith(matrix.asset, 'kernel-nvidia-gpu') }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: kata-artifacts-arm64-${{ matrix.asset }}-modules${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}-modules.tar.zst
name: kata-artifacts-arm64-${{ matrix.asset }}-headers${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}-headers.tar.zst
retention-days: 15
if-no-files-found: error
build-asset-rootfs:
name: build-asset-rootfs
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
needs: build-asset
permissions:
contents: read
@@ -151,8 +150,8 @@ jobs:
matrix:
asset:
- rootfs-image
- rootfs-image-nvidia-gpu
- rootfs-initrd
- rootfs-initrd-nvidia-gpu
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
@@ -210,13 +209,13 @@ jobs:
# We don't need the binaries installed in the rootfs as part of the release tarball, so can delete them now we've built the rootfs
remove-rootfs-binary-artifacts:
name: remove-rootfs-binary-artifacts
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
needs: build-asset-rootfs
strategy:
matrix:
asset:
- busybox
- kernel-nvidia-gpu-modules
- kernel-nvidia-gpu-headers
steps:
- uses: geekyeggo/delete-artifact@f275313e70c08f6120db482d7a6b98377786765b # v5.1.0
with:
@@ -225,7 +224,7 @@ jobs:
# We don't need the binaries installed in the rootfs as part of the release tarball, so can delete them now we've built the rootfs
remove-rootfs-binary-artifacts-for-release:
name: remove-rootfs-binary-artifacts-for-release
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
needs: build-asset-rootfs
strategy:
matrix:
@@ -239,7 +238,7 @@ jobs:
build-asset-shim-v2:
name: build-asset-shim-v2
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
needs: [build-asset, build-asset-rootfs, remove-rootfs-binary-artifacts, remove-rootfs-binary-artifacts-for-release]
permissions:
contents: read
@@ -299,7 +298,7 @@ jobs:
create-kata-tarball:
name: create-kata-tarball
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
needs: [build-asset, build-asset-rootfs, build-asset-shim-v2]
permissions:
contents: read
@@ -327,16 +326,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -32,7 +32,7 @@ jobs:
permissions:
contents: read
packages: write
runs-on: ubuntu-24.04-ppc64le
runs-on: ppc64le-small
strategy:
matrix:
asset:
@@ -89,7 +89,7 @@ jobs:
build-asset-rootfs:
name: build-asset-rootfs
runs-on: ubuntu-24.04-ppc64le
runs-on: ppc64le-small
needs: build-asset
permissions:
contents: read
@@ -170,7 +170,7 @@ jobs:
build-asset-shim-v2:
name: build-asset-shim-v2
runs-on: ubuntu-24.04-ppc64le
runs-on: ppc64le-small
needs: [build-asset, build-asset-rootfs, remove-rootfs-binary-artifacts]
permissions:
contents: read
@@ -230,7 +230,7 @@ jobs:
create-kata-tarball:
name: create-kata-tarball
runs-on: ubuntu-24.04-ppc64le
runs-on: ppc64le-small
needs: [build-asset, build-asset-rootfs, build-asset-shim-v2]
permissions:
contents: read
@@ -262,16 +262,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -20,6 +20,9 @@ on:
required: false
type: string
default: ""
secrets:
QUAY_DEPLOYER_PASSWORD:
required: true
permissions: {}
@@ -38,6 +41,14 @@ jobs:
- kernel
- virtiofsd
steps:
- name: Login to Kata Containers quay.io
if: ${{ inputs.push-to-registry == 'yes' }}
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: quay.io
username: ${{ vars.QUAY_DEPLOYER_USERNAME }}
password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
@@ -71,5 +82,5 @@ jobs:
with:
name: kata-artifacts-riscv64-${{ matrix.asset }}${{ inputs.tarball-suffix }}
path: kata-build/kata-static-${{ matrix.asset }}.tar.zst
retention-days: 3
retention-days: 15
if-no-files-found: error

View File

@@ -32,7 +32,7 @@ permissions: {}
jobs:
build-asset:
name: build-asset
runs-on: ubuntu-24.04-s390x
runs-on: s390x
permissions:
contents: read
packages: write
@@ -44,6 +44,7 @@ jobs:
- agent
- coco-guest-components
- kernel
- kernel-confidential
- pause-image
- qemu
- virtiofsd
@@ -256,7 +257,7 @@ jobs:
build-asset-shim-v2:
name: build-asset-shim-v2
runs-on: ubuntu-24.04-s390x
runs-on: s390x
needs: [build-asset, build-asset-rootfs, remove-rootfs-binary-artifacts]
permissions:
contents: read
@@ -318,7 +319,7 @@ jobs:
create-kata-tarball:
name: create-kata-tarball
runs-on: ubuntu-24.04-s390x
runs-on: s390x
needs:
- build-asset
- build-asset-rootfs
@@ -350,16 +351,6 @@ jobs:
./tools/packaging/kata-deploy/local-build/kata-deploy-merge-builds.sh kata-artifacts versions.yaml
env:
RELEASE: ${{ inputs.stage == 'release' && 'yes' || 'no' }}
- name: Check kata tarball size (GitHub release asset limit)
run: |
# https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases#storage-and-bandwidth-quotas
GITHUB_ASSET_MAX_BYTES=2147483648
tarball_size=$(stat -c "%s" kata-static.tar.zst)
if [[ "${tarball_size}" -ge "${GITHUB_ASSET_MAX_BYTES}" ]]; then
echo "::error::tarball size (${tarball_size} bytes) >= GitHub release asset limit (${GITHUB_ASSET_MAX_BYTES} bytes)"
exit 1
fi
echo "tarball size: ${tarball_size} bytes"
- name: store-artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:

View File

@@ -1,75 +0,0 @@
name: Build kubectl multi-arch image
on:
schedule:
# Run every Sunday at 00:00 UTC
- cron: '0 0 * * 0'
workflow_dispatch:
# Allow manual triggering
push:
branches:
- main
paths:
- 'tools/packaging/kubectl/Dockerfile'
- '.github/workflows/build-kubectl-image.yaml'
permissions: {}
env:
REGISTRY: quay.io
IMAGE_NAME: kata-containers/kubectl
jobs:
build-and-push:
name: Build and push multi-arch image
runs-on: ubuntu-24.04
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Set up QEMU
uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Login to Quay.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ${{ env.REGISTRY }}
username: ${{ vars.QUAY_DEPLOYER_USERNAME }}
password: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
- name: Get kubectl version
id: kubectl-version
run: |
KUBECTL_VERSION=$(curl -L -s https://dl.k8s.io/release/stable.txt)
echo "version=${KUBECTL_VERSION}" >> "$GITHUB_OUTPUT"
- name: Generate image metadata
id: meta
uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
tags: |
type=raw,value=latest
type=raw,value={{date 'YYYYMMDD'}}
type=raw,value=${{ steps.kubectl-version.outputs.version }}
type=sha,prefix=
- name: Build and push multi-arch image
uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25 # v5.4.0
with:
context: tools/packaging/kubectl/
file: tools/packaging/kubectl/Dockerfile
platforms: linux/amd64,linux/arm64,linux/s390x,linux/ppc64le
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max

View File

@@ -17,7 +17,6 @@ jobs:
pr-number: "dev"
tag: ${{ github.sha }}-dev
target-branch: ${{ github.ref_name }}
extensive-matrix-autogenerated-policy: "yes"
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}

View File

@@ -1,34 +0,0 @@
on:
schedule:
- cron: '0 5 * * *'
name: Nightly CI for RISC-V
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: {}
jobs:
build-kata-static-tarball-riscv:
permissions:
contents: read
packages: write
id-token: write
attestations: write
uses: ./.github/workflows/build-kata-static-tarball-riscv64.yaml
with:
tarball-suffix: -${{ github.sha }}
commit-hash: ${{ github.sha }}
target-branch: ${{ github.ref_name }}
build-checks-preview:
strategy:
fail-fast: false
matrix:
instance:
- "riscv-builder"
uses: ./.github/workflows/build-checks-preview-riscv64.yaml
with:
instance: ${{ matrix.instance }}

View File

@@ -22,7 +22,6 @@ jobs:
pr-number: "nightly"
tag: ${{ github.sha }}-nightly
target-branch: ${{ github.ref_name }}
extensive-matrix-autogenerated-policy: "yes"
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AZ_APPID: ${{ secrets.AZ_APPID }}

View File

@@ -19,10 +19,6 @@ on:
required: false
type: string
default: no
extensive-matrix-autogenerated-policy:
required: false
type: string
default: no
secrets:
AUTHENTICATED_IMAGE_PASSWORD:
required: true
@@ -106,7 +102,7 @@ jobs:
tag: ${{ inputs.tag }}-arm64
commit-hash: ${{ inputs.commit-hash }}
target-branch: ${{ inputs.target-branch }}
runner: ubuntu-24.04-arm
runner: ubuntu-22.04-arm
arch: arm64
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
@@ -138,6 +134,20 @@ jobs:
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
build-kata-static-tarball-riscv64:
permissions:
contents: read
packages: write
id-token: write
attestations: write
uses: ./.github/workflows/build-kata-static-tarball-riscv64.yaml
with:
tarball-suffix: -${{ inputs.tag }}
commit-hash: ${{ inputs.commit-hash }}
target-branch: ${{ inputs.target-branch }}
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
publish-kata-deploy-payload-s390x:
needs: build-kata-static-tarball-s390x
permissions:
@@ -151,7 +161,7 @@ jobs:
tag: ${{ inputs.tag }}-s390x
commit-hash: ${{ inputs.commit-hash }}
target-branch: ${{ inputs.target-branch }}
runner: ubuntu-24.04-s390x
runner: s390x
arch: s390x
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
@@ -169,7 +179,7 @@ jobs:
tag: ${{ inputs.tag }}-ppc64le
commit-hash: ${{ inputs.commit-hash }}
target-branch: ${{ inputs.target-branch }}
runner: ubuntu-24.04-ppc64le
runner: ppc64le-small
arch: ppc64le
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
@@ -216,6 +226,61 @@ jobs:
platforms: linux/amd64, linux/s390x
file: tests/integration/kubernetes/runtimeclass_workloads/confidential/unencrypted/Dockerfile
publish-csi-driver-amd64:
name: publish-csi-driver-amd64
needs: build-kata-static-tarball-amd64
permissions:
contents: read
packages: write
runs-on: ubuntu-22.04
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-amd64-${{ inputs.tag }}
path: kata-artifacts
- name: Install tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-artifacts
- name: Copy binary into Docker context
run: |
# Copy to the location where the Dockerfile expects the binary.
mkdir -p src/tools/csi-kata-directvolume/bin/
cp /opt/kata/bin/csi-kata-directvolume src/tools/csi-kata-directvolume/bin/directvolplugin
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Login to Kata Containers ghcr.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Docker build and push
uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25 # v5.4.0
with:
tags: ghcr.io/kata-containers/csi-kata-directvolume:${{ inputs.pr-number }}
push: true
context: src/tools/csi-kata-directvolume/
platforms: linux/amd64
file: src/tools/csi-kata-directvolume/Dockerfile
run-kata-monitor-tests:
if: ${{ inputs.skip-test != 'yes' }}
needs: build-kata-static-tarball-amd64
@@ -246,21 +311,6 @@ jobs:
AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}
AZ_SUBSCRIPTION_ID: ${{ secrets.AZ_SUBSCRIPTION_ID }}
run-k8s-tests-on-free-runner:
if: ${{ inputs.skip-test != 'yes' }}
needs: publish-kata-deploy-payload-amd64
permissions:
contents: read
uses: ./.github/workflows/run-k8s-tests-on-free-runner.yaml
with:
tarball-suffix: -${{ inputs.tag }}
registry: ghcr.io
repo: ${{ github.repository_owner }}/kata-deploy-ci
tag: ${{ inputs.tag }}-amd64
commit-hash: ${{ inputs.commit-hash }}
pr-number: ${{ inputs.pr-number }}
target-branch: ${{ inputs.target-branch }}
run-k8s-tests-on-arm64:
if: ${{ inputs.skip-test != 'yes' }}
needs: publish-kata-deploy-payload-arm64
@@ -278,7 +328,6 @@ jobs:
needs: publish-kata-deploy-payload-amd64
uses: ./.github/workflows/run-k8s-tests-on-nvidia-gpu.yaml
with:
tarball-suffix: -${{ inputs.tag }}
registry: ghcr.io
repo: ${{ github.repository_owner }}/kata-deploy-ci
tag: ${{ inputs.tag }}-amd64
@@ -294,6 +343,7 @@ jobs:
needs:
- publish-kata-deploy-payload-amd64
- build-and-publish-tee-confidential-unencrypted-image
- publish-csi-driver-amd64
uses: ./.github/workflows/run-kata-coco-tests.yaml
permissions:
contents: read
@@ -306,7 +356,6 @@ jobs:
commit-hash: ${{ inputs.commit-hash }}
pr-number: ${{ inputs.pr-number }}
target-branch: ${{ inputs.target-branch }}
extensive-matrix-autogenerated-policy: ${{ inputs.extensive-matrix-autogenerated-policy }}
secrets:
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AZ_APPID: ${{ secrets.AZ_APPID }}
@@ -438,7 +487,7 @@ jobs:
vmm: ${{ matrix.params.vmm }}
run-cri-containerd-tests-arm64:
if: false
if: ${{ inputs.skip-test != 'yes' }}
needs: build-kata-static-tarball-arm64
strategy:
fail-fast: false

View File

@@ -72,7 +72,7 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
build-mode: ${{ matrix.build-mode }}
@@ -95,6 +95,6 @@ jobs:
make -C src/runtime
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"

View File

@@ -31,22 +31,10 @@ jobs:
with:
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Install Rust
run: ./tests/install_rust.sh

View File

@@ -24,22 +24,10 @@ jobs:
fetch-depth: 0
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Docs URL Alive Check
run: |

View File

@@ -1,53 +0,0 @@
name: Documentation
on:
push:
branches:
- main
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
build:
runs-on: ubuntu-24.04
name: Build docs
permissions:
contents: read
pages: write
id-token: write
steps:
- uses: actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b # v5.0.0
- uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5.0.1
with:
persist-credentials: false
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: 3.x
- run: pip install -r docs/requirements.txt
- run: python3 -m mkdocs build --config-file ./mkdocs.yaml --site-dir site/
id: build
- uses: actions/upload-pages-artifact@7b1f4a764d45c48632c6b24a0339c27f5614fb0b # v4.0.0
id: deployment
with:
path: site/
name: github-pages
deploy:
needs: build
runs-on: ubuntu-24.04
name: Deploy docs
permissions:
pages: write
id-token: write
environment:
name: github-pages
url: ${{ steps.deployment.outputs.page_url }}
steps:
- name: Deploy to GitHub Pages
uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e # v4.0.5
id: deployment
with:
artifact_name: github-pages

View File

@@ -1,29 +0,0 @@
name: EditorConfig checker
on:
pull_request:
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
editorconfig-checker:
name: editorconfig-checker
runs-on: ubuntu-24.04
steps:
- name: Checkout the code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
persist-credentials: false
- name: Set up editorconfig-checker
uses: editorconfig-checker/action-editorconfig-checker@4b6cd6190d435e7e084fb35e36a096e98506f7b9 # v2.1.0
with:
version: v3.6.1
- name: Run editorconfig-checker
run: editorconfig-checker

View File

@@ -10,9 +10,7 @@ on:
- opened
- synchronize
- reopened
- edited
- labeled
- unlabeled
permissions: {}

View File

@@ -27,22 +27,10 @@ jobs:
fetch-depth: 0
persist-credentials: false
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "${GITHUB_PATH}"
- name: Install govulncheck
run: |

View File

@@ -0,0 +1,43 @@
name: kata-runtime-classes-sync
on:
pull_request:
types:
- opened
- edited
- reopened
- synchronize
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
kata-deploy-runtime-classes-check:
name: kata-deploy-runtime-classes-check
runs-on: ubuntu-22.04
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Ensure the split out runtime classes match the all-in-one file
run: |
pushd tools/packaging/kata-deploy/runtimeclasses/
echo "::group::Combine runtime classes"
for runtimeClass in $(find . -type f \( -name "*.yaml" -and -not -name "kata-runtimeClasses.yaml" \) | sort); do
echo "Adding ${runtimeClass} to the resultingRuntimeClasses.yaml"
cat "${runtimeClass}" >> resultingRuntimeClasses.yaml;
done
echo "::endgroup::"
echo "::group::Displaying the content of resultingRuntimeClasses.yaml"
cat resultingRuntimeClasses.yaml
echo "::endgroup::"
echo ""
echo "::group::Displaying the content of kata-runtimeClasses.yaml"
cat kata-runtimeClasses.yaml
echo "::endgroup::"
echo ""
diff resultingRuntimeClasses.yaml kata-runtimeClasses.yaml

View File

@@ -19,25 +19,23 @@ permissions: {}
jobs:
scan-scheduled:
name: Scan of whole repo
permissions:
actions: read # # Required to upload SARIF file to CodeQL
contents: read # Read commit contents
security-events: write # Require writing security events to upload SARIF file to security tab
if: ${{ github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@8ae4be80636b94886b3c271caad730985ce0611c" # v2.3.3
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@b00f71e051ddddc6e46a193c31c8c0bf283bf9e6" # v2.1.0
with:
scan-args: |-
-r
./
scan-pr:
name: Scan of just PR code
permissions:
actions: read # Required to upload SARIF file to CodeQL
contents: read # Read commit contents
security-events: write # Require writing security events to upload SARIF file to security tab
if: ${{ github.event_name == 'pull_request' }}
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable-pr.yml@8ae4be80636b94886b3c271caad730985ce0611c" # v2.3.3
uses: "google/osv-scanner-action/.github/workflows/osv-scanner-reusable-pr.yml@b00f71e051ddddc6e46a193c31c8c0bf283bf9e6" # v2.1.0
with:
# Example of specifying custom arguments
scan-args: |-

View File

@@ -97,7 +97,7 @@ jobs:
repo: kata-containers/kata-deploy-ci
tag: kata-containers-latest-arm64
target-branch: ${{ github.ref_name }}
runner: ubuntu-24.04-arm
runner: ubuntu-22.04-arm
arch: arm64
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}
@@ -131,7 +131,7 @@ jobs:
repo: kata-containers/kata-deploy-ci
tag: kata-containers-latest-ppc64le
target-branch: ${{ github.ref_name }}
runner: ubuntu-24.04-ppc64le
runner: ppc64le-small
arch: ppc64le
secrets:
QUAY_DEPLOYER_PASSWORD: ${{ secrets.QUAY_DEPLOYER_PASSWORD }}

View File

@@ -50,24 +50,6 @@ jobs:
fetch-depth: 0
persist-credentials: false
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"

View File

@@ -1,43 +0,0 @@
# Push gperf and busybox tarballs to the ORAS cache (ghcr.io) so that
# download-with-oras-cache.sh can pull them instead of hitting upstream.
# Runs when versions.yaml changes on main (e.g. after a PR merge) or manually.
name: CI | Push ORAS tarball cache
on:
push:
branches:
- main
paths:
- 'versions.yaml'
workflow_dispatch:
permissions: {}
jobs:
push-oras-cache:
name: push-oras-cache
runs-on: ubuntu-22.04
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
persist-credentials: false
- name: Install yq
run: ./ci/install_yq.sh
- name: Install ORAS
uses: oras-project/setup-oras@22ce207df3b08e061f537244349aac6ae1d214f6 # v1.2.4
with:
version: "1.2.0"
- name: Populate ORAS tarball cache
run: ./tools/packaging/scripts/populate-oras-tarball-cache.sh all
env:
ARTEFACT_REGISTRY: ghcr.io
ARTEFACT_REPOSITORY: kata-containers
ARTEFACT_REGISTRY_USERNAME: ${{ github.actor }}
ARTEFACT_REGISTRY_PASSWORD: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -34,7 +34,7 @@ jobs:
permissions:
contents: read
packages: write
runs-on: ubuntu-24.04-arm
runs-on: ubuntu-22.04-arm
steps:
- name: Login to Kata Containers ghcr.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0

View File

@@ -31,7 +31,7 @@ jobs:
permissions:
contents: read
packages: write
runs-on: ubuntu-24.04-ppc64le
runs-on: ppc64le-small
steps:
- name: Login to Kata Containers ghcr.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0

View File

@@ -35,7 +35,7 @@ jobs:
permissions:
contents: read
packages: write
runs-on: ubuntu-24.04-s390x
runs-on: s390x
steps:
- name: Login to Kata Containers ghcr.io
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0

View File

@@ -181,23 +181,6 @@ jobs:
GH_TOKEN: ${{ github.token }}
ARCHITECTURE: ppc64le
- name: Set KATA_TOOLS_STATIC_TARBALL env var
run: |
tarball=$(pwd)/kata-tools-static.tar.zst
echo "KATA_TOOLS_STATIC_TARBALL=${tarball}" >> "$GITHUB_ENV"
- name: Download amd64 tools artifacts
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64
- name: Upload amd64 static tarball tools to GitHub
run: |
./tools/packaging/release/release.sh upload-kata-tools-static-tarball
env:
GH_TOKEN: ${{ github.token }}
ARCHITECTURE: amd64
upload-versions-yaml:
name: upload-versions-yaml
needs: release

View File

@@ -0,0 +1,167 @@
name: CI | Run containerd guest pull stability tests
on:
schedule:
- cron: "0 */1 * * *" #run every hour
permissions: {}
# This job relies on k8s pre-installed using kubeadm
jobs:
run-containerd-guest-pull-stability-tests:
name: run-containerd-guest-pull-stability-tests-${{ matrix.environment.test-type }}-${{ matrix.environment.containerd }}
strategy:
fail-fast: false
matrix:
environment: [
{ test-type: multi-snapshotter, containerd: v2.2 },
{ test-type: force-guest-pull, containerd: v1.7 },
{ test-type: force-guest-pull, containerd: v2.0 },
{ test-type: force-guest-pull, containerd: v2.1 },
{ test-type: force-guest-pull, containerd: v2.2 },
]
env:
# I don't want those to be inside double quotes, so I'm deliberately ignoring the double quotes here.
IMAGES_LIST: quay.io/mongodb/mongodb-community-server@sha256:8b73733842da21b6bbb6df4d7b2449229bb3135d2ec8c6880314d88205772a11 ghcr.io/edgelesssys/redis@sha256:ecb0a964c259a166a1eb62f0eb19621d42bd1cce0bc9bb0c71c828911d4ba93d
runs-on: containerd-${{ matrix.environment.test-type }}-${{ matrix.environment.containerd }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Rotate the journal
run: sudo journalctl --rotate --vacuum-time 1s
- name: Pull the kata-deploy image to be used
run: sudo ctr -n k8s.io image pull quay.io/kata-containers/kata-deploy-ci:kata-containers-latest
- name: Deploy Kata Containers
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
env:
KATA_HYPERVISOR: qemu-coco-dev
KUBERNETES: vanilla
SNAPSHOTTER: ${{ matrix.environment.test-type == 'multi-snapshotter' && 'nydus' || '' }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.test-type == 'multi-snapshotter' }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.test-type == 'force-guest-pull' && 'qemu-coco-dev' || '' }}
# This is needed as we may hit the createContainerTimeout
- name: Adjust Kata Containers' create_container_timeout
run: |
sudo sed -i -e 's/^\(create_container_timeout\).*=.*$/\1 = 600/g' /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
grep "create_container_timeout.*=" /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
# This is needed in order to have enough tmpfs space inside the guest to pull the image
- name: Adjust Kata Containers' default_memory
run: |
sudo sed -i -e 's/^\(default_memory\).*=.*$/\1 = 4096/g' /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
grep "default_memory.*=" /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
- name: Run a few containers using overlayfs
run: |
# I don't want those to be inside double quotes, so I'm deliberately ignoring the double quotes here
# shellcheck disable=SC2086
for img in ${IMAGES_LIST}; do
echo "overlayfs | Using on image: ${img}"
pod="$(echo ${img} | tr ':.@/' '-' | awk '{print substr($0,1,56)}')"
kubectl run "${pod}" \
-it --rm \
--restart=Never \
--image="${img}" \
--image-pull-policy=Always \
--pod-running-timeout=10m \
-- uname -r
done
- name: Run a the same few containers using a different snapshotter
run: |
# I don't want those to be inside double quotes, so I'm deliberately ignoring the double quotes here
# shellcheck disable=SC2086
for img in ${IMAGES_LIST}; do
echo "nydus | Using on image: ${img}"
pod="kata-$(echo ${img} | tr ':.@/' '-' | awk '{print substr($0,1,56)}')"
kubectl run "${pod}" \
-it --rm \
--restart=Never \
--image="${img}" \
--image-pull-policy=Always \
--pod-running-timeout=10m \
--overrides='{
"spec": {
"runtimeClassName": "kata-qemu-coco-dev"
}
}' \
-- uname -r
done
- name: Uninstall Kata Containers
run: bash tests/integration/kubernetes/gha-run.sh cleanup
env:
KATA_HYPERVISOR: qemu-coco-dev
KUBERNETES: vanilla
SNAPSHOTTER: nydus
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: true
- name: Run a few containers using overlayfs
run: |
# I don't want those to be inside double quotes, so I'm deliberately ignoring the double quotes here
# shellcheck disable=SC2086
for img in ${IMAGES_LIST}; do
echo "overlayfs | Using on image: ${img}"
pod="$(echo ${img} | tr ':.@/' '-' | awk '{print substr($0,1,56)}')"
kubectl run "${pod}" \
-it --rm \
--restart=Never \
--image=${img} \
--image-pull-policy=Always \
--pod-running-timeout=10m \
-- uname -r
done
- name: Deploy Kata Containers
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
env:
KATA_HYPERVISOR: qemu-coco-dev
KUBERNETES: vanilla
SNAPSHOTTER: nydus
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: true
# This is needed as we may hit the createContainerTimeout
- name: Adjust Kata Containers' create_container_timeout
run: |
sudo sed -i -e 's/^\(create_container_timeout\).*=.*$/\1 = 600/g' /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
grep "create_container_timeout.*=" /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
# This is needed in order to have enough tmpfs space inside the guest to pull the image
- name: Adjust Kata Containers' default_memory
run: |
sudo sed -i -e 's/^\(default_memory\).*=.*$/\1 = 4096/g' /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
grep "default_memory.*=" /opt/kata/share/defaults/kata-containers/configuration-qemu-coco-dev.toml
- name: Run a the same few containers using a different snapshotter
run: |
# I don't want those to be inside double quotes, so I'm deliberately ignoring the double quotes here
# shellcheck disable=SC2086
for img in ${IMAGES_LIST}; do
echo "nydus | Using on image: ${img}"
pod="kata-$(echo ${img} | tr ':.@/' '-' | awk '{print substr($0,1,56)}')"
kubectl run "${pod}" \
-it --rm \
--restart=Never \
--image="${img}" \
--image-pull-policy=Always \
--pod-running-timeout=10m \
--overrides='{
"spec": {
"runtimeClassName": "kata-qemu-coco-dev"
}
}' \
-- uname -r
done
- name: Uninstall Kata Containers
run: bash tests/integration/kubernetes/gha-run.sh cleanup || true
if: always()
env:
KATA_HYPERVISOR: qemu-coco-dev
KUBERNETES: vanilla
SNAPSHOTTER: nydus
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: true

View File

@@ -35,6 +35,8 @@ on:
jobs:
run-cri-containerd:
name: run-cri-containerd-${{ inputs.arch }} (${{ inputs.containerd_version }}, ${{ inputs.vmm }})
strategy:
fail-fast: false
runs-on: ${{ inputs.runner }}
env:
CONTAINERD_VERSION: ${{ inputs.containerd_version }}
@@ -53,25 +55,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: ${{ inputs.arch == 'ppc64le' && 'ppc64le' || '' }}
- name: Install dependencies
timeout-minutes: 15
run: bash tests/integration/cri-containerd/gha-run.sh install-dependencies

View File

@@ -42,6 +42,17 @@ jobs:
strategy:
fail-fast: false
matrix:
host_os:
- ubuntu
vmm:
- clh
- dragonball
- qemu
- qemu-runtime-rs
- cloud-hypervisor
instance-type:
- small
- normal
include:
- host_os: cbl-mariner
vmm: clh
@@ -69,7 +80,6 @@ jobs:
KUBERNETES: "vanilla"
K8S_TEST_HOST_TYPE: ${{ matrix.instance-type }}
GENPOLICY_PULL_METHOD: ${{ matrix.genpolicy-pull-method }}
RUNS_ON_AKS: "true"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -83,14 +93,14 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Install kata
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-artifacts
- name: Download Azure CLI
uses: azure/setup-kubectl@776406bce94f63e41d621b960d78ee25c8b76ede # v4.0.1
@@ -132,10 +142,6 @@ jobs:
timeout-minutes: 60
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Refresh OIDC token in case access token expired
if: always()
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0

View File

@@ -32,7 +32,6 @@ jobs:
matrix:
vmm:
- qemu
- qemu-runtime-rs
k8s:
- kubeadm
runs-on: arm64-k8s
@@ -69,10 +68,6 @@ jobs:
timeout-minutes: 30
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Collect artifacts ${{ matrix.vmm }}
if: always()
run: bash tests/integration/kubernetes/gha-run.sh collect-artifacts

View File

@@ -1,127 +0,0 @@
# Run Kubernetes integration tests on free GitHub runners with a locally
# deployed cluster (kubeadm).
name: CI | Run kubernetes tests on free runner
on:
workflow_call:
inputs:
tarball-suffix:
required: false
type: string
registry:
required: true
type: string
repo:
required: true
type: string
tag:
required: true
type: string
pr-number:
required: true
type: string
commit-hash:
required: false
type: string
target-branch:
required: false
type: string
default: ""
permissions: {}
jobs:
run-k8s-tests:
name: run-k8s-tests
strategy:
fail-fast: false
matrix:
environment: [
{ vmm: clh, containerd_version: lts },
{ vmm: clh, containerd_version: active },
{ vmm: dragonball, containerd_version: lts },
{ vmm: dragonball, containerd_version: active },
{ vmm: qemu, containerd_version: lts },
{ vmm: qemu, containerd_version: active },
{ vmm: qemu-runtime-rs, containerd_version: lts },
{ vmm: qemu-runtime-rs, containerd_version: active },
{ vmm: cloud-hypervisor, containerd_version: lts },
{ vmm: cloud-hypervisor, containerd_version: active },
]
runs-on: ubuntu-24.04
permissions:
contents: read
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HOST_OS: ubuntu
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KUBERNETES: vanilla
K8S_TEST_HOST_TYPE: baremetal-no-attestation
CONTAINER_ENGINE: containerd
CONTAINER_ENGINE_VERSION: ${{ matrix.environment.containerd_version }}
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Deploy k8s (kubeadm)
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Run tests
timeout-minutes: 60
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup

View File

@@ -1,10 +1,7 @@
name: CI | Run NVIDIA GPU kubernetes tests on amd64
name: CI | Run NVIDIA GPU kubernetes tests on arm64
on:
workflow_call:
inputs:
tarball-suffix:
required: true
type: string
registry:
required: true
type: string
@@ -48,10 +45,7 @@ jobs:
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KUBERNETES: kubeadm
KBS: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'true' || 'false' }}
SNAPSHOTTER: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'nydus' || '' }}
USE_EXPERIMENTAL_SNAPSHOTTER_SETUP: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'true' || 'false' }}
K8S_TEST_HOST_TYPE: baremetal
K8S_TEST_HOST_TYPE: all
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -65,33 +59,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Uninstall previous `kbs-client`
if: matrix.environment.name != 'nvidia-gpu'
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh uninstall-kbs-client
- name: Deploy CoCo KBS
if: matrix.environment.name != 'nvidia-gpu'
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
env:
NVIDIA_VERIFIER_MODE: remote
KBS_INGRESS: nodeport
- name: Install `kbs-client`
if: matrix.environment.name != 'nvidia-gpu'
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
@@ -100,15 +67,10 @@ jobs:
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Run tests ${{ matrix.environment.vmm }}
timeout-minutes: 60
timeout-minutes: 30
run: bash tests/integration/kubernetes/gha-run.sh run-nv-tests
env:
NGC_API_KEY: ${{ secrets.NGC_API_KEY }}
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Collect artifacts ${{ matrix.environment.vmm }}
if: always()
run: bash tests/integration/kubernetes/gha-run.sh collect-artifacts
@@ -125,9 +87,3 @@ jobs:
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always() && matrix.environment.name != 'nvidia-gpu'
timeout-minutes: 10
run: |
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs

View File

@@ -57,24 +57,10 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install yq
- name: Install golang
run: |
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
run: |
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
# Setup-go doesn't work properly with ppc64le: https://github.com/actions/setup-go/issues/648
architecture: 'ppc64le'
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Prepare the runner for k8s test suite
run: bash "${HOME}/scripts/k8s_cluster_prepare.sh"
@@ -89,7 +75,3 @@ jobs:
- name: Run tests
timeout-minutes: 30
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests

View File

@@ -131,18 +131,12 @@ jobs:
timeout-minutes: 60
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh cleanup-zvsi
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: |
if [ "${KBS}" == "true" ]; then
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs

View File

@@ -46,7 +46,6 @@ jobs:
matrix:
vmm:
- qemu-coco-dev
- qemu-coco-dev-runtime-rs
snapshotter:
- nydus
pull-type:
@@ -84,14 +83,14 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Install kata
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-artifacts
- name: Log into the Azure account
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
@@ -140,10 +139,6 @@ jobs:
timeout-minutes: 300
run: bash tests/stability/gha-stability-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Refresh OIDC token in case access token expired
if: always()
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0

View File

@@ -24,10 +24,6 @@ on:
required: false
type: string
default: ""
extensive-matrix-autogenerated-policy:
required: false
type: string
default: no
secrets:
AUTHENTICATED_IMAGE_PASSWORD:
required: true
@@ -83,15 +79,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
@@ -110,6 +97,10 @@ jobs:
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 100
run: bash tests/integration/kubernetes/gha-run.sh run-tests
@@ -120,52 +111,57 @@ jobs:
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: |
[[ "${KATA_HYPERVISOR}" == "qemu-tdx" ]] && echo "ITA_KEY=${GH_ITA_KEY}" >> "${GITHUB_ENV}"
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
- name: Delete CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh delete-csi-driver
# Generate jobs for testing CoCo on non-TEE environments
run-k8s-tests-coco-nontee:
name: run-k8s-tests-coco-nontee
strategy:
fail-fast: false
matrix:
environment: [
{ vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
]
runs-on: ubuntu-24.04
vmm:
- qemu-coco-dev
snapshotter:
- nydus
pull-type:
- guest-pull
include:
- pull-type: experimental-force-guest-pull
snapshotter: ""
runs-on: ubuntu-22.04
permissions:
contents: read
id-token: write # Used for OIDC access to log into Azure
environment: ci
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KATA_HYPERVISOR: ${{ matrix.vmm }}
# Some tests rely on that variable to run (or not)
KBS: "true"
# Set the KBS ingress handler (empty string disables handling)
KBS_INGRESS: "nodeport"
KBS_INGRESS: "aks"
KUBERNETES: "vanilla"
PULL_TYPE: ${{ matrix.environment.pull_type }}
PULL_TYPE: ${{ matrix.pull-type }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
SNAPSHOTTER: ${{ matrix.environment.snapshotter }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && matrix.environment.vmm || '' }}
AUTO_GENERATE_POLICY: "yes"
SNAPSHOTTER: ${{ matrix.snapshotter }}
# Caution: current ingress controller used to expose the KBS service
# requires much vCPUs, lefting only a few for the tests. Depending on the
# host type chose it will result on the creation of a cluster with
# insufficient resources.
K8S_TEST_HOST_TYPE: "all"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "active"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -179,45 +175,49 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Install kata
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Log into the Azure account
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Create AKS cluster
uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # v3.0.2
with:
timeout_minutes: 15
max_attempts: 20
retry_on: error
retry_wait_seconds: 10
command: bash tests/integration/kubernetes/gha-run.sh create-cluster
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Install `kubectl`
uses: azure/setup-kubectl@776406bce94f63e41d621b960d78ee25c8b76ede # v4.0.1
with:
version: 'latest'
- name: Download credentials for the Kubernetes CLI to use them
run: bash tests/integration/kubernetes/gha-run.sh get-cluster-credentials
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
env:
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.snapshotter == 'nydus' }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && env.KATA_HYPERVISOR || '' }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ env.SNAPSHOTTER == 'nydus' }}
AUTO_GENERATE_POLICY: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && 'no' || 'yes' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
@@ -227,126 +227,9 @@ jobs:
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
# Extensive matrix: autogenerated policy tests (nydus + experimental-force-guest-pull) on k0s, k3s, rke2, microk8s with qemu-coco-dev / qemu-coco-dev-runtime-rs
run-k8s-tests-coco-nontee-extensive-matrix:
if: ${{ inputs.extensive-matrix-autogenerated-policy == 'yes' }}
name: run-k8s-tests-coco-nontee-extensive-matrix
strategy:
fail-fast: false
matrix:
environment: [
{ k8s: k0s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k0s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: k0s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: k3s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: rke2, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
{ k8s: microk8s, vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
]
runs-on: ubuntu-24.04
permissions:
contents: read
environment: ci
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KBS: "true"
KBS_INGRESS: "nodeport"
KUBERNETES: ${{ matrix.environment.k8s }}
SNAPSHOTTER: ${{ matrix.environment.snapshotter }}
PULL_TYPE: ${{ matrix.environment.pull_type }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && matrix.environment.vmm || '' }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
AUTO_GENERATE_POLICY: "yes"
K8S_TEST_HOST_TYPE: "all"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Deploy ${{ matrix.environment.k8s }}
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
env:
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.snapshotter == 'nydus' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
- name: Install `kbs-client`
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
@@ -356,15 +239,17 @@ jobs:
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
- name: Refresh OIDC token in case access token expired
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Delete CoCo KBS
- name: Delete AKS cluster
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
run: bash tests/integration/kubernetes/gha-run.sh delete-cluster
# Generate jobs for testing CoCo on non-TEE environments with erofs-snapshotter
run-k8s-tests-coco-nontee-with-erofs-snapshotter:
@@ -392,7 +277,7 @@ jobs:
KBS_INGRESS: ""
KUBERNETES: "vanilla"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "active"
CONTAINER_ENGINE_VERSION: "v2.2"
PULL_TYPE: ${{ matrix.pull-type }}
SNAPSHOTTER: ${{ matrix.snapshotter }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: "true"
@@ -400,7 +285,6 @@ jobs:
# We are skipping the auto generated policy tests for now,
# but those should be enabled as soon as we work on that.
AUTO_GENERATE_POLICY: "no"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -414,15 +298,6 @@ jobs:
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tools-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-tools-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-tools-artifacts
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
@@ -431,6 +306,7 @@ jobs:
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
@@ -444,6 +320,8 @@ jobs:
- name: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
env:
GH_TOKEN: ${{ github.token }}
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
@@ -452,6 +330,10 @@ jobs:
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
@@ -459,8 +341,3 @@ jobs:
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh cleanup

View File

@@ -102,10 +102,6 @@ jobs:
- name: Run tests
run: bash tests/functional/kata-deploy/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Refresh OIDC token in case access token expired
if: always()
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0

View File

@@ -66,6 +66,7 @@ jobs:
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
@@ -84,7 +85,3 @@ jobs:
- name: Run tests
run: bash tests/functional/kata-deploy/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/functional/kata-deploy/gha-run.sh report-tests

54
.github/workflows/run-runk-tests.yaml vendored Normal file
View File

@@ -0,0 +1,54 @@
name: CI | Run runk tests
on:
workflow_call:
inputs:
tarball-suffix:
required: false
type: string
commit-hash:
required: false
type: string
target-branch:
required: false
type: string
default: ""
permissions: {}
jobs:
run-runk:
name: run-runk
# Skip runk tests as we have no maintainers. TODO: Decide when to remove altogether
if: false
runs-on: ubuntu-22.04
env:
CONTAINERD_VERSION: lts
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Install dependencies
run: bash tests/integration/runk/gha-run.sh install-dependencies
env:
GH_TOKEN: ${{ github.token }}
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata
run: bash tests/integration/runk/gha-run.sh install-kata kata-artifacts
- name: Run runk tests
run: bash tests/integration/runk/gha-run.sh run

View File

@@ -55,6 +55,6 @@ jobs:
# Upload the results to GitHub's code scanning dashboard (optional).
# Commenting out will disable upload of results to your repo's Code Scanning dashboard
- name: "Upload to code-scanning"
uses: github/codeql-action/upload-sarif@4bdb89f48054571735e3792627da6195c57459e2 # v3.31.10
uses: github/codeql-action/upload-sarif@v3
with:
sarif_file: results.sarif

View File

@@ -1,30 +0,0 @@
name: Spelling check
on: ["pull_request"]
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
check-spelling:
name: check-spelling
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
fetch-depth: 0
persist-credentials: false
- name: Check Spelling
uses: streetsidesoftware/cspell-action@9cd41bb518a24fefdafd9880cbab8f0ceba04d28 # 8.3.0
with:
files: |
**/*.md
**/*.rst
**/*.txt
incremental_files_only: true
config: ".cspell.yaml"

View File

@@ -6,21 +6,14 @@ on:
permissions: {}
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
stale:
name: stale
runs-on: ubuntu-22.04
permissions:
actions: write # Needed to manage caches for state persistence across runs
pull-requests: write # Needed to add/remove labels, post comments, or close PRs
steps:
- uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9.1.0
with:
stale-pr-message: 'This PR has been opened without activity for 180 days. Please comment on the issue or it will be closed in 7 days.'
stale-pr-message: 'This PR has been opened without with no activity for 180 days. Comment on the issue otherwise it will be closed in 7 days'
days-before-pr-stale: 180
days-before-pr-close: 7
days-before-issue-stale: -1

View File

@@ -28,9 +28,21 @@ jobs:
fail-fast: false
matrix:
instance:
- "ubuntu-24.04-arm"
- "ubuntu-24.04-s390x"
- "ubuntu-22.04-arm"
- "s390x"
- "ubuntu-24.04-ppc64le"
uses: ./.github/workflows/build-checks.yaml
with:
instance: ${{ matrix.instance }}
build-checks-preview:
needs: skipper
if: ${{ needs.skipper.outputs.skip_static != 'yes' }}
strategy:
fail-fast: false
matrix:
instance:
- "riscv-builder"
uses: ./.github/workflows/build-checks-preview-riscv64.yaml
with:
instance: ${{ matrix.instance }}

View File

@@ -126,19 +126,14 @@ jobs:
./ci/install_yq.sh
env:
INSTALL_IN_GOPATH: false
- name: Read properties from versions.yaml
- name: Install golang
run: |
cd "${GOPATH}/src/github.com/${GITHUB_REPOSITORY}"
go_version="$(yq '.languages.golang.version' versions.yaml)"
[ -n "$go_version" ]
echo "GO_VERSION=${go_version}" >> "$GITHUB_ENV"
- name: Setup Golang version ${{ env.GO_VERSION }}
uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
with:
go-version: ${{ env.GO_VERSION }}
./tests/install_go.sh -f -p
echo "/usr/local/go/bin" >> "$GITHUB_PATH"
- name: Install system dependencies
run: |
sudo apt-get update && sudo apt-get -y install moreutils
sudo apt-get update && sudo apt-get -y install moreutils hunspell hunspell-en-gb hunspell-en-us pandoc
- name: Install open-policy-agent
run: |
cd "${GOPATH}/src/github.com/${GITHUB_REPOSITORY}"

View File

@@ -21,7 +21,7 @@ jobs:
persist-credentials: false
- name: Run zizmor
uses: zizmorcore/zizmor-action@135698455da5c3b3e55f73f4419e481ab68cdd95 # v0.4.1
uses: zizmorcore/zizmor-action@e673c3917a1aef3c65c972347ed84ccd013ecda4 # v0.2.0
with:
advanced-security: false
annotations: true

5
.gitignore vendored
View File

@@ -18,8 +18,3 @@ src/tools/log-parser/kata-log-parser
tools/packaging/static-build/agent/install_libseccomp.sh
.envrc
.direnv
**/.DS_Store
site/
opt/
tools/packaging/kernel/configs/**/.config
root_hash.txt

View File

@@ -1,146 +0,0 @@
[workspace.package]
authors = ["The Kata Containers community <kata-dev@lists.katacontainers.io>"]
edition = "2018"
license = "Apache-2.0"
rust-version = "1.88"
[workspace]
members = [
# Dragonball
"src/dragonball",
"src/dragonball/dbs_acpi",
"src/dragonball/dbs_address_space",
"src/dragonball/dbs_allocator",
"src/dragonball/dbs_arch",
"src/dragonball/dbs_boot",
"src/dragonball/dbs_device",
"src/dragonball/dbs_interrupt",
"src/dragonball/dbs_legacy_devices",
"src/dragonball/dbs_pci",
"src/dragonball/dbs_tdx",
"src/dragonball/dbs_upcall",
"src/dragonball/dbs_utils",
"src/dragonball/dbs_virtio_devices",
# genpolicy
"src/tools/genpolicy",
# runtime-rs
"src/runtime-rs",
"src/runtime-rs/crates/agent",
"src/runtime-rs/crates/hypervisor",
"src/runtime-rs/crates/persist",
"src/runtime-rs/crates/resource",
"src/runtime-rs/crates/runtimes",
"src/runtime-rs/crates/service",
"src/runtime-rs/crates/shim",
"src/runtime-rs/crates/shim-ctl",
"src/runtime-rs/tests/utils",
]
resolver = "2"
# TODO: Add all excluded crates to root workspace
exclude = [
"src/agent",
"src/tools",
"src/libs",
# kata-deploy binary is standalone and has its own Cargo.toml for now
"tools/packaging/kata-deploy/binary",
# We are cloning and building rust packages under
# "tools/packaging/kata-deploy/local-build/build" folder, which may mislead
# those packages to think they are part of the kata root workspace
"tools/packaging/kata-deploy/local-build/build",
]
[workspace.dependencies]
# Rust-VMM crates
event-manager = "0.4.0"
kvm-bindings = "0.14.0"
kvm-ioctls = "0.24.0"
linux-loader = "0.13.0"
seccompiler = "0.5.0"
vfio-bindings = "0.6.1"
vfio-ioctls = "0.5.0"
virtio-bindings = "0.2.0"
virtio-queue = "0.17.0"
vm-fdt = "0.3.0"
vm-memory = "=0.17.1"
vm-superio = "0.8.0"
vmm-sys-util = "0.15.0"
# Local dependencies from Dragonball Sandbox crates
dragonball = { path = "src/dragonball" }
dbs-acpi = { path = "src/dragonball/dbs_acpi" }
dbs-address-space = { path = "src/dragonball/dbs_address_space" }
dbs-allocator = { path = "src/dragonball/dbs_allocator" }
dbs-arch = { path = "src/dragonball/dbs_arch" }
dbs-boot = { path = "src/dragonball/dbs_boot" }
dbs-device = { path = "src/dragonball/dbs_device" }
dbs-interrupt = { path = "src/dragonball/dbs_interrupt" }
dbs-legacy-devices = { path = "src/dragonball/dbs_legacy_devices" }
dbs-pci = { path = "src/dragonball/dbs_pci" }
dbs-tdx = { path = "src/dragonball/dbs_tdx" }
dbs-upcall = { path = "src/dragonball/dbs_upcall" }
dbs-utils = { path = "src/dragonball/dbs_utils" }
dbs-virtio-devices = { path = "src/dragonball/dbs_virtio_devices" }
# Local dependencies from runtime-rs
agent = { path = "src/runtime-rs/crates/agent" }
hypervisor = { path = "src/runtime-rs/crates/hypervisor" }
persist = { path = "src/runtime-rs/crates/persist" }
resource = { path = "src/runtime-rs/crates/resource" }
runtimes = { path = "src/runtime-rs/crates/runtimes" }
service = { path = "src/runtime-rs/crates/service" }
tests_utils = { path = "src/runtime-rs/tests/utils" }
ch-config = { path = "src/runtime-rs/crates/hypervisor/ch-config" }
common = { path = "src/runtime-rs/crates/runtimes/common" }
linux_container = { path = "src/runtime-rs/crates/runtimes/linux_container" }
virt_container = { path = "src/runtime-rs/crates/runtimes/virt_container" }
wasm_container = { path = "src/runtime-rs/crates/runtimes/wasm_container" }
# Local dependencies from `src/lib`
kata-sys-util = { path = "src/libs/kata-sys-util" }
kata-types = { path = "src/libs/kata-types", features = ["safe-path"] }
logging = { path = "src/libs/logging" }
protocols = { path = "src/libs/protocols", features = ["async"] }
runtime-spec = { path = "src/libs/runtime-spec" }
safe-path = { path = "src/libs/safe-path" }
shim-interface = { path = "src/libs/shim-interface" }
test-utils = { path = "src/libs/test-utils" }
# Local dependencies from `src/agent`
kata-agent-policy = { path = "src/agent/policy" }
# Outside dependencies
actix-rt = "2.7.0"
anyhow = "1.0"
async-trait = "0.1.48"
containerd-shim = { version = "0.10.0", features = ["async"] }
containerd-shim-protos = { version = "0.10.0", features = ["async"] }
go-flag = "0.1.0"
hyper = "0.14.20"
hyperlocal = "0.8.0"
lazy_static = "1.4"
libc = "0.2"
log = "0.4.14"
netns-rs = "0.1.0"
# Note: nix needs to stay sync'd with libs versions
nix = "0.26.4"
oci-spec = { version = "0.8.1", features = ["runtime"] }
protobuf = "3.7.2"
rand = "0.8.4"
serde = { version = "1.0.145", features = ["derive"] }
serde_json = "1.0.91"
sha2 = "0.10.9"
slog = "2.5.2"
slog-scope = "4.4.0"
strum = { version = "0.24.0", features = ["derive"] }
tempfile = "3.19.1"
thiserror = "1.0"
tokio = "1.46.1"
tracing = "0.1.41"
tracing-opentelemetry = "0.18.0"
ttrpc = "0.8.4"
url = "2.5.4"

View File

@@ -18,6 +18,7 @@ TOOLS =
TOOLS += agent-ctl
TOOLS += kata-ctl
TOOLS += log-parser
TOOLS += runk
TOOLS += trace-forwarder
STANDARD_TARGETS = build check clean install static-checks-build test vendor
@@ -47,13 +48,7 @@ docs-url-alive-check:
bash ci/docs-url-alive-check.sh
build-and-publish-kata-debug:
bash tools/packaging/kata-debug/kata-debug-build-and-upload-payload.sh ${KATA_DEBUG_REGISTRY} ${KATA_DEBUG_TAG}
docs-build:
docker build -t kata-docs:latest -f ./docs/Dockerfile ./docs
docs-serve: docs-build
docker run --rm -p 8000:8000 -v ${PWD}:/docs:ro kata-docs:latest serve --config-file /docs/mkdocs.yaml -a 0.0.0.0:8000
bash tools/packaging/kata-debug/kata-debug-build-and-upload-payload.sh ${KATA_DEBUG_REGISTRY} ${KATA_DEBUG_TAG}
.PHONY: \
all \
@@ -61,6 +56,4 @@ docs-serve: docs-build
install-tarball \
default \
static-checks \
docs-url-alive-check \
docs-build \
docs-serve
docs-url-alive-check

View File

@@ -139,6 +139,7 @@ The table below lists the remaining parts of the project:
| [`agent-ctl`](src/tools/agent-ctl) | utility | Tool that provides low-level access for testing the agent. |
| [`kata-ctl`](src/tools/kata-ctl) | utility | Tool that provides advanced commands and debug facilities. |
| [`trace-forwarder`](src/tools/trace-forwarder) | utility | Agent tracing helper. |
| [`runk`](src/tools/runk) | utility | Standard OCI container runtime based on the agent. |
| [`ci`](.github/workflows) | CI | Continuous Integration configuration files and scripts. |
| [`ocp-ci`](ci/openshift-ci/README.md) | CI | Continuous Integration configuration for the OpenShift pipelines. |
| [`katacontainers.io`](https://github.com/kata-containers/www.katacontainers.io) | Source for the [`katacontainers.io`](https://www.katacontainers.io) site. |

View File

@@ -1 +1 @@
3.28.0
3.22.0

View File

@@ -378,7 +378,7 @@ that is used in the test" section. From there you can see exactly what you'll
have to use when deploying kata-deploy in your local cluster.
> [!NOTE]
> TODO: @wainersm TO FINISH THIS PART BASED ON HIS PR TO RUN A LOCAL CI
> TODO: WAINER TO FINISH THIS PART BASED ON HIS PR TO RUN A LOCAL CI
## Adding new runners

View File

@@ -11,10 +11,6 @@ script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "${script_dir}/../tests/common.bash"
# Path to the ORAS cache helper for downloading tarballs (sourced when needed)
# Use ORAS_CACHE_HELPER env var (set by build.sh in Docker) or fallback to repo path
oras_cache_helper="${ORAS_CACHE_HELPER:-${script_dir}/../tools/packaging/scripts/download-with-oras-cache.sh}"
# The following variables if set on the environment will change the behavior
# of gperf and libseccomp configure scripts, that may lead this script to
# fail. So let's ensure they are unset here.
@@ -48,9 +44,6 @@ fi
gperf_tarball="gperf-${gperf_version}.tar.gz"
gperf_tarball_url="${gperf_url}/${gperf_tarball}"
# Use ORAS cache for gperf downloads (gperf upstream can be unreliable)
USE_ORAS_CACHE="${USE_ORAS_CACHE:-yes}"
# We need to build the libseccomp library from sources to create a static
# library for the musl libc.
# However, ppc64le, riscv64 and s390x have no musl targets in Rust. Hence, we do
@@ -75,23 +68,7 @@ trap finish EXIT
build_and_install_gperf() {
echo "Build and install gperf version ${gperf_version}"
mkdir -p "${gperf_install_dir}"
# Use ORAS cache if available and enabled
if [[ "${USE_ORAS_CACHE}" == "yes" ]] && [[ -f "${oras_cache_helper}" ]]; then
echo "Using ORAS cache for gperf download"
source "${oras_cache_helper}"
local cached_tarball
cached_tarball=$(download_component gperf "$(pwd)")
if [[ -f "${cached_tarball}" ]]; then
gperf_tarball="${cached_tarball}"
else
echo "ORAS cache download failed, falling back to direct download"
curl -sLO "${gperf_tarball_url}"
fi
else
curl -sLO "${gperf_tarball_url}"
fi
curl -sLO "${gperf_tarball_url}"
tar -xf "${gperf_tarball}"
pushd "gperf-${gperf_version}"
# Unset $CC for configure, we will always use native for gperf

View File

@@ -73,12 +73,12 @@ function install_yq() {
goarch=arm64
;;
"arm64")
# If we're on an apple silicon machine, just assign amd64.
# The version of yq we use doesn't have a darwin arm build,
# If we're on an apple silicon machine, just assign amd64.
# The version of yq we use doesn't have a darwin arm build,
# but Rosetta can come to the rescue here.
if [[ ${goos} == "Darwin" ]]; then
goarch=amd64
else
else
goarch=arm64
fi
;;

View File

@@ -98,7 +98,7 @@ Let's say the OCP pipeline passed running with
but failed running with
``quay.io/kata-containers/kata-deploy-ci:kata-containers-9f512c016e75599a4a921bd84ea47559fe610057-amd64``
and you'd like to know which PR caused the regression. You can either run with
all the 60 tags between or you can utilize the [`bisecter`](https://github.com/ldoktor/bisecter)
all the 60 tags between or you can utilize the [bisecter](https://github.com/ldoktor/bisecter)
to optimize the number of steps in between.
Before running the bisection you need a reproducer script. Sample one called

View File

@@ -46,12 +46,16 @@ fi
[[ ${SELINUX_PERMISSIVE} == "yes" ]] && oc delete -f "${deployments_dir}/machineconfig_selinux.yaml.in"
# Delete kata-containers
helm uninstall kata-deploy --wait --namespace kube-system
pushd "${katacontainers_repo_dir}/tools/packaging/kata-deploy" || { echo "Failed to push to ${katacontainers_repo_dir}/tools/packaging/kata-deploy"; exit 125; }
oc delete -f kata-deploy/base/kata-deploy.yaml
oc -n kube-system wait --timeout=10m --for=delete -l name=kata-deploy pod
oc apply -f kata-cleanup/base/kata-cleanup.yaml
echo "Wait for all related pods to be gone"
( repeats=1; for _ in $(seq 1 600); do
oc get pods -l name="kubelet-kata-cleanup" --no-headers=true -n kube-system 2>&1 | grep "No resources found" -q && ((repeats++)) || repeats=1
[[ "${repeats}" -gt 5 ]] && echo kata-cleanup finished && break
sleep 1
done) || { echo "There are still some kata-cleanup related pods after 600 iterations"; oc get all -n kube-system; exit 1; }
oc delete -f kata-cleanup/base/kata-cleanup.yaml
oc delete -f kata-rbac/base/kata-rbac.yaml
oc delete -f runtimeclasses/kata-runtimeClasses.yaml

View File

@@ -51,13 +51,13 @@ apply_kata_deploy() {
oc label --overwrite ns kube-system pod-security.kubernetes.io/enforce=privileged pod-security.kubernetes.io/warn=baseline pod-security.kubernetes.io/audit=baseline
local version chart
version='0.0.0-dev'
version=$(curl -sSL https://api.github.com/repos/kata-containers/kata-containers/releases/latest | jq .tag_name | tr -d '"')
chart="oci://ghcr.io/kata-containers/kata-deploy-charts/kata-deploy"
# Ensure any potential leftover is cleaned up ... and this secret usually is not in case of previous failures
oc delete secret sh.helm.release.v1.kata-deploy.v1 -n kube-system || true
echo "Installing kata using helm ${chart} ${version} (sha printed in helm output)"
echo "Installing kata using helm ${chart} ${version}"
helm install kata-deploy --wait --namespace kube-system --set "image.reference=${KATA_DEPLOY_IMAGE%%:*},image.tag=${KATA_DEPLOY_IMAGE##*:}" "${chart}" --version "${version}"
}

View File

@@ -157,16 +157,6 @@ if [[ -z "${CAA_IMAGE}" ]]; then
fi
# Get latest PP image
#
# You can list the CI images by:
# az sig image-version list-community --location "eastus" --public-gallery-name "cocopodvm-d0e4f35f-5530-4b9c-8596-112487cdea85" --gallery-image-definition "podvm_image0" --output table
# or the release images by:
# az sig image-version list-community --location "eastus" --public-gallery-name "cococommunity-42d8482d-92cd-415b-b332-7648bd978eff" --gallery-image-definition "peerpod-podvm-fedora" --output table
# or the release debug images by:
# az sig image-version list-community --location "eastus" --public-gallery-name "cococommunity-42d8482d-92cd-415b-b332-7648bd978eff" --gallery-image-definition "peerpod-podvm-fedora-debug" --output table
#
# Note there are other flavours of the released images, you can list them by:
# az sig image-definition list-community --location "eastus" --public-gallery-name "cococommunity-42d8482d-92cd-415b-b332-7648bd978eff" --output table
if [[ -z "${PP_IMAGE_ID}" ]]; then
SUCCESS_TIME=$(curl -s \
-H "Accept: application/vnd.github+json" \

View File

@@ -1,18 +0,0 @@
# https://lukasgeiter.github.io/mkdocs-awesome-nav/
nav:
- Home: index.md
- Getting Started:
- prerequisites.md
- installation.md
- Configuration:
- helm-configuration.md
- runtime-configuration.md
- Platform Support:
- hypervisors.md
- Guides:
- Use Cases:
- NVIDIA GPU Passthrough: use-cases/NVIDIA-GPU-passthrough-and-Kata-QEMU.md
- NVIDIA vGPU: use-cases/NVIDIA-GPU-passthrough-and-Kata.md
- Intel Discrete GPU: use-cases/Intel-Discrete-GPU-passthrough-and-Kata.md
- Misc:
- Architecture: design/architecture/

View File

@@ -83,4 +83,4 @@ files to the repository and create a pull request when you are ready.
If you have an idea for a blog post and would like to get feedback from the
community about it or have any questions about the process, please reach out
on one of the community's [communication channels](https://katacontainers.io/community/).
on one of the community's [communication channels](https://katacontainers.io/community/).

View File

@@ -125,7 +125,7 @@ If you want to enable SELinux in Permissive mode, add `enforcing=0` to the kerne
Enable full debug as follows:
```bash
$ sudo sed -i -E 's/^(\s*enable_debug\s*=\s*)false/\1true/' /etc/kata-containers/configuration.toml
$ sudo sed -i -e 's/^# *\(enable_debug\).*=.*$/\1 = true/g' /etc/kata-containers/configuration.toml
$ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.log=debug initcall_debug"/g' /etc/kata-containers/configuration.toml
```
@@ -289,14 +289,14 @@ provided by your distribution.
As a prerequisite, you need to install Docker. Otherwise, you will not be
able to run the `rootfs.sh` script with `USE_DOCKER=true` as expected in
the following example. Specifying the `OS_VERSION` is required when using `distro="ubuntu"`.
the following example.
```bash
$ export distro="ubuntu" # example
$ export ROOTFS_DIR="$(realpath kata-containers/tools/osbuilder/rootfs-builder/rootfs)"
$ sudo rm -rf "${ROOTFS_DIR}"
$ pushd kata-containers/tools/osbuilder/rootfs-builder
$ script -fec 'sudo -E USE_DOCKER=true OS_VERSION=noble ./rootfs.sh "${distro}"'
$ script -fec 'sudo -E USE_DOCKER=true ./rootfs.sh "${distro}"'
$ popd
```
@@ -730,7 +730,7 @@ sudo sed -i -e 's/^kernel_params = "\(.*\)"/kernel_params = "\1 agent.debug_cons
##### Connecting to the debug console
Next, connect to the debug console. The VSOCK paths vary slightly between each
Next, connect to the debug console. The VSOCKS paths vary slightly between each
VMM solution.
In case of cloud-hypervisor, connect to the `vsock` as shown:

View File

@@ -1,11 +0,0 @@
# Copyright 2026 Kata Contributors
#
# SPDX-License-Identifier: Apache-2.0
#
FROM python:3.12-slim
WORKDIR /
COPY ./requirements.txt requirements.txt
RUN pip install --no-cache-dir -r requirements.txt
ENTRYPOINT ["python3", "-m", "mkdocs"]

View File

@@ -188,14 +188,15 @@ and compare them with standard tools (e.g. `diff(1)`).
# Spelling
Since this project uses a number of terms not found in conventional
dictionaries, we have a [kata-dictionary](../tests/spellcheck/kata-dictionary.txt)
that contains some project specific terms we use.
dictionaries, we have a
[spell checking tool](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-spelling)
that checks both dictionary words and the additional terms we use.
You can run the `cspell` checking tool on your document before raising a PR to ensure it
Run the spell checking tool on your document before raising a PR to ensure it
is free of mistakes.
If your document introduces new terms, you need to update the custom
dictionary to incorporate the new words.
dictionary used by the spell checking tool to incorporate the new words.
# Names

View File

@@ -187,10 +187,9 @@ different compared to `runc` containers:
into the guest and exposes it directly to the container.
**Mounting guest devices**: When the source path of a hostPath volume is
under `/dev` (or `/dev` itself), and the path corresponds to a
non-regular file (i.e., a device, directory, or any other special file)
or is not accessible by the Kata shim, the Kata agent bind mounts the
source path directly from the *guest* filesystem into the container.
under `/dev`, and the path either corresponds to a host device or is not
accessible by the Kata shim, the Kata agent bind mounts the source path
directly from the *guest* filesystem into the container.
[runtime-config]: /src/runtime/README.md#configuration
[k8s-hostpath]: https://kubernetes.io/docs/concepts/storage/volumes/#hostpath
@@ -207,7 +206,7 @@ For security reasons, the following mounts are disallowed:
| `proc \|\| sysfs` | `*` | not a directory (e.g. symlink) | CVE-2019-19921 |
For bind mounts under /proc, these destinations are allowed:
* `/proc/cpuinfo`
* `/proc/diskstats`
* `/proc/meminfo`
@@ -227,35 +226,6 @@ Importantly, the default behavior to pass the host devices to a
privileged container is not supported in Kata Containers and needs to be
disabled, see [Privileged Kata Containers](how-to/privileged.md).
## Guest pulled container images
When using features like **nydus guest-pull**, set user/group IDs explicitly in the pod spec.
If the ID values are omitted:
- Your workload might be executed with unexpected user/group ID values, because image layers
may be unavailable to containerd, so image config (including user/group) is not applied.
- If using policy or genpolicy, the generated policy may detect these unexpected values and
reject the creation of workload containers.
Set `securityContext` explicitly. Use **pod-level** `spec.securityContext` (for Pods) or
`spec.template.spec.securityContext` (for controllers like Deployments) and/or **container-level**
`spec.containers[].securityContext`. Include at least:
- `runAsUser` — primary user ID
- `runAsGroup` — primary group ID
- `fsGroup` — volume group ownership (often reflected as a supplemental group)
- `supplementalGroups` — list of additional group IDs (if needed)
Example:
```yaml
# Explicit user/group/supplementary groups to support nydus guest-pull
securityContext:
runAsUser: 0
runAsGroup: 0
fsGroup: 0
supplementalGroups: [1, 2, 3, 4, 6, 10, 11, 20, 26, 27]
```
# Appendices
## The constraints challenge

View File

@@ -83,7 +83,3 @@ Documents that help to understand and contribute to Kata Containers.
If you have a suggestion for how we can improve the
[website](https://katacontainers.io), please raise an issue (or a PR) on
[the repository that holds the source for the website](https://github.com/OpenStackweb/kata-netlify-refresh).
### Toolchain Guidance
* [Toolchain Guidance](./Toochain-Guidance.md)

View File

@@ -1,69 +1,59 @@
# How to do a Kata Containers Release
This document lists the tasks required to create a Kata Release.
## Requirements
- GitHub permissions to run workflows.
## Release Model
## Versioning
Kata Containers follows a rolling release model with monthly snapshots.
New features, bug fixes, and improvements are continuously integrated into
`main`. Each month, a snapshot is tagged as a new `MINOR` release.
The Kata Containers project uses [semantic versioning](http://semver.org/) for all releases.
Semantic versions are comprised of three fields in the form:
### Versioning
```
MAJOR.MINOR.PATCH
```
Releases use the `MAJOR.MINOR.PATCH` scheme. Monthly snapshots increment
`MINOR`; `PATCH` is typically `0`. Major releases are rare (years apart) and
signal significant architectural changes that may require updates to container
managers (Containerd, CRI-O) or other infrastructure. Breaking changes in
`MINOR` releases are avoided where possible, but may occasionally occur as
features are deprecated or removed.
When `MINOR` increases, the new release adds **new features** but *without changing the existing behavior*.
### No Stable Branches
When `MAJOR` increases, the new release adds **new features, bug fixes, or
both** and which **changes the behavior from the previous release** (incompatible with previous releases).
The Kata Containers project does not maintain stable branches (see
[#9064](https://github.com/kata-containers/kata-containers/issues/9064)).
Bug fixes land on `main` and ship in the next monthly snapshot rather than
being backported. Downstream projects that need extended support or compliance
certifications should select a monthly snapshot as their stable base and manage
their own validation and patch backporting from there.
A major release will also likely require a change of the container manager version used,
-for example Containerd or CRI-O. Please refer to the release notes for further details.
**Important** : the Kata Containers project doesn't have stable branches (see
[this issue](https://github.com/kata-containers/kata-containers/issues/9064) for details).
Bug fixes are released as part of `MINOR` or `MAJOR` releases only. `PATCH` is always `0`.
## Release Process
### Lock the `main` branch and announce release process
In order to prevent any PRs getting merged during the release process, and
slowing the release process down, by impacting the payload caches, we have
recently trialed setting the `main` branch to read-only.
Once the `kata-containers/kata-containers` repository is ready for a new
release, lock the main branch until the release action has completed.
Notify the #kata-dev Slack channel about the ongoing release process.
Ideally, CI usage by others should be reduced to a minimum during the
ongoing release process.
> [!NOTE]
> Admin permission is needed to lock/unlock the `main` branch.
### Bump the `VERSION` and `Chart.yaml` file
Create a PR to set the release in the [`VERSION`](./../VERSION) file and to
update the `version` and `appVersion` fields in the
[`Chart.yaml`](./../tools/packaging/kata-deploy/helm-chart/kata-deploy/Chart.yaml)
file. Temporarily unlock the main branch to merge the PR.
When the `kata-containers/kata-containers` repository is ready for a new release,
first create a PR to set the release in the [`VERSION`](./../VERSION) file and update the
`version` and `appVersion` in the
[`Chart.yaml`](./../tools/packaging/kata-deploy/helm-chart/kata-deploy/Chart.yaml) file and
have it merged.
### Lock the `main` branch
In order to prevent any PRs getting merged during the release process, and slowing the release
process down, by impacting the payload caches, we have recently trailed setting the `main`
branch to read only whilst the release action runs.
> [!NOTE]
> Admin permission is needed to complete this task.
### Wait for the `VERSION` bump PR payload publish to complete
To reduce the chance of need to re-run the release workflow, check the [CI |
Publish Kata Containers
payload](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml)
To reduce the chance of need to re-run the release workflow, check the
[CI | Publish Kata Containers payload](https://github.com/kata-containers/kata-containers/actions/workflows/payload-after-push.yaml)
once the `VERSION` PR bump has merged to check that the assets build correctly
and are cached, so that the release process can just download these artifacts
rather than needing to build them all, which takes time and can reveal errors in
infra.
rather than needing to build them all, which takes time and can reveal errors in infra.
### Trigger the `Release Kata Containers` GitHub Action
### Check GitHub Actions
We make use of [GitHub actions](https://github.com/features/actions) in the
[release](https://github.com/kata-containers/kata-containers/actions/workflows/release.yaml)
@@ -73,10 +63,11 @@ release artifacts.
> [!NOTE]
> Write permissions to trigger the action.
The action is manually triggered and is responsible for generating a new release
(including a new tag), pushing those to the `kata-containers/kata-containers`
repository. The new release is initially created as a draft. It is promoted to
an official release when the whole workflow has completed successfully.
The action is manually triggered and is responsible for generating a new
release (including a new tag), pushing those to the
`kata-containers/kata-containers` repository. The new release is initially
created as a draft. It is promoted to an official release when the whole
workflow has completed successfully.
Check the [actions status
page](https://github.com/kata-containers/kata-containers/actions) to verify all
@@ -84,13 +75,12 @@ steps in the actions workflow have completed successfully. On success, a static
tarball containing Kata release artifacts will be uploaded to the [Release
page](https://github.com/kata-containers/kata-containers/releases).
If the workflow fails because of some external environmental causes, e.g.
network timeout, simply re-run the failed jobs until they eventually succeed.
If the workflow fails because of some external environmental causes, e.g. network
timeout, simply re-run the failed jobs until they eventually succeed.
If for some reason you need to cancel the workflow or re-run it entirely, go
first to the [Release
page](https://github.com/kata-containers/kata-containers/releases) and delete
the draft release from the previous run.
If for some reason you need to cancel the workflow or re-run it entirely, go first
to the [Release page](https://github.com/kata-containers/kata-containers/releases) and
delete the draft release from the previous run.
### Unlock the `main` branch
@@ -100,8 +90,9 @@ an admin to do it.
### Improve the release notes
Release notes are auto-generated by the GitHub CLI tool used as part of our
release workflow. However, some manual tweaking may still be necessary in order
to highlight the most important features and bug fixes in a specific release.
release workflow. However, some manual tweaking may still be necessary in
order to highlight the most important features and bug fixes in a specific
release.
With this in mind, please, poke @channel on #kata-dev and people who worked on
the release will be able to contribute to that.

View File

@@ -1,39 +0,0 @@
# Toolchains
As a community we want to strike a balance between having up-to-date toolchains, to receive the
latest security fixes and to be able to benefit from new features and packages, whilst not being
too bleeding edge and disrupting downstream and other consumers. As a result we have the following
guidelines (note, not hard rules) for our go and rust toolchains that we are attempting to try out:
## Go toolchain
Go is released [every six months](https://go.dev/wiki/Go-Release-Cycle) with support for the
[last two major release versions](https://go.dev/doc/devel/release#policy). We always want to
ensure that we are on a supported version so we receive security fixes. To try and make
things easier for some of our users, we aim to be using the older of the two supported major
versions, unless there is a compelling reason to adopt the newer version.
In practice this means that we bump our major version of the go toolchain every six months to
version (1.x-1) in response to a new version (1.x) coming out, which makes our current version
(1.x-2) no longer supported. We will bump the minor version whenever required to satisfy
dependency updates, or security fixes.
Our go toolchain version is recorded in [`versions.yaml`](../versions.yaml) under
`.languages.golang.version` and should match with the version in our `go.mod` files.
## Rust toolchain
Rust has a [six week](https://doc.rust-lang.org/book/appendix-05-editions.html#:~:text=The%20Rust%20language%20and%20compiler,these%20tiny%20changes%20add%20up.)
release cycle and they only support the latest stable release, so if we wanted to remain on a
supported release we would only ever build with the latest stable and bump every 6 weeks.
However feedback from our community has indicated that this is a challenge as downstream consumers
often want to get rust from their distro, or downstream fork and these struggle to keep up with
the six week release schedule. As a result the community has agreed to try out a policy of
"stable-2", where we aim to build with a rust version that is two versions behind the latest stable
version.
In practice this should mean that we bump our rust toolchain every six weeks, to version
1.x-2 when 1.x is released as stable and we should be picking up the latest point release
of that version, if there were any.
The rust-toolchain that we are using is recorded in [`rust-toolchain.toml`](../rust-toolchain.toml).

View File

@@ -198,7 +198,7 @@ fn join_params_with_dash(str: &str, num: i32) -> Result<String> {
return Err("number must be positive");
}
let result = format!("{str}-{num}");
let result = format!("{}-{}", str, num);
Ok(result)
}
@@ -253,13 +253,13 @@ mod tests {
// Run the tests
for (i, d) in tests.iter().enumerate() {
// Create a string containing details of the test
let msg = format!("test[{i}]: {d:?}");
let msg = format!("test[{}]: {:?}", i, d);
// Call the function under test
let result = join_params_with_dash(d.str, d.num);
// Update the test details string with the results of the call
let msg = format!("{msg}, result: {result:?}");
let msg = format!("{}, result: {:?}", msg, result);
// Perform the checks
if d.result.is_ok() {
@@ -267,8 +267,8 @@ mod tests {
continue;
}
let expected_error = format!("{d.result.as_ref().unwrap_err()}");
let actual_error = format!("{result.unwrap_err()}");
let expected_error = format!("{}", d.result.as_ref().unwrap_err());
let actual_error = format!("{}", result.unwrap_err());
assert!(actual_error == expected_error, msg);
}
}

View File

@@ -1,9 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32">
<!-- Dark background matching the site -->
<rect width="32" height="32" rx="4" fill="#1a1a2e"/>
<!-- Kata logo scaled and centered -->
<g transform="translate(-27, -2) scale(0.75)">
<path d="M70.925 25.22L58.572 37.523 46.27 25.22l2.192-2.192 10.11 10.11 10.11-10.11zm-6.575-.2l-3.188-3.188 3.188-3.188 3.188 3.188zm-4.93-2.54l3.736 3.736-3.736 3.736zm-1.694 7.422l-8.07-8.07 8.07-8.07zm1.694-16.14l3.686 3.686-3.686 3.686zm-13.15 4.682L58.572 6.143l12.353 12.303-2.192 2.192-10.16-10.11-10.11 10.11zm26.997 0L58.572 3.752 43.878 18.446l3.387 3.387-3.387 3.387 14.694 14.694L73.266 25.22l-3.337-3.387z" fill="#f15b3e"/>
</g>
</svg>

Before

Width:  |  Height:  |  Size: 710 B

View File

@@ -231,6 +231,12 @@ Run the
[markdown checker](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-markdown)
on your documentation changes.
### Spell check
Run the
[spell checker](https://github.com/kata-containers/kata-containers/tree/main/tests/cmd/check-spelling)
on your documentation changes.
## Finally
You may wish to read the documentation that the

View File

@@ -4,7 +4,7 @@ As we know, we can interact with cgroups in two ways, **`cgroupfs`** and **`syst
## usage
For systemd, kata agent configures cgroups according to the following `linux.cgroupsPath` format standard provided by `runc` (`[slice]:[prefix]:[name]`). If you don't provide a valid `linux.cgroupsPath`, kata agent will treat it as `"system.slice:kata_agent:<container-id>"`.
For systemd, kata agent configures cgroups according to the following `linux.cgroupsPath` format standard provided by `runc` (`[slice]:[prefix]:[name]`). If you don't provide a valid `linux.cgroupsPath`, kata agent will treat it as `"system.slice:kata_agent:<container-id>"`.
> Here slice is a systemd slice under which the container is placed. If empty, it defaults to system.slice, except when cgroup v2 is used and rootless container is created, in which case it defaults to user.slice.
>
@@ -65,7 +65,7 @@ The kata agent will translate the parameters in the `linux.resources` of `config
## Systemd Interface
`session.rs` and `system.rs` in `src/agent/rustjail/src/cgroups/systemd/interface` are automatically generated by `zbus-xmlgen`, which is is an accompanying tool provided by `zbus` to generate Rust code from `D-Bus XML interface descriptions`. The specific commands to generate these two files are as follows:
`session.rs` and `system.rs` in `src/agent/rustjail/src/cgroups/systemd/interface` are automatically generated by `zbus-xmlgen`, which is is an accompanying tool provided by `zbus` to generate Rust code from `D-Bus XML interface descriptions`. The specific commands to generate these two files are as follows:
```shell
// system.rs

View File

@@ -10,7 +10,7 @@ participant proxy
#Docker Exec
Docker->kata-runtime: exec
kata-runtime->virtcontainers: EnterContainer()
virtcontainers->agent: exec
virtcontainers->agent: exec
agent->virtcontainers: Process started in the container
virtcontainers->shim: start shim
shim->agent: ReadStdout()

View File

@@ -322,7 +322,7 @@ The runtime is responsible for starting the [hypervisor](#hypervisor)
and it's VM, and communicating with the [agent](#agent) using a
[ttRPC based protocol](#agent-communications-protocol) over a VSOCK
socket that provides a communications link between the VM and the
host.
host.
This protocol allows the runtime to send container management commands
to the agent. The protocol is also used to carry the standard I/O

View File

@@ -4,15 +4,15 @@ Containers typically live in their own, possibly shared, networking namespace.
At some point in a container lifecycle, container engines will set up that namespace
to add the container to a network which is isolated from the host network.
In order to setup the network for a container, container engines call into a
In order to setup the network for a container, container engines call into a
networking plugin. The network plugin will usually create a virtual
ethernet (`veth`) pair adding one end of the `veth` pair into the container
networking namespace, while the other end of the `veth` pair is added to the
ethernet (`veth`) pair adding one end of the `veth` pair into the container
networking namespace, while the other end of the `veth` pair is added to the
host networking namespace.
This is a very namespace-centric approach as many hypervisors or VM
Managers (VMMs) such as `virt-manager` cannot handle `veth`
interfaces. Typically, [`TAP`](https://www.kernel.org/doc/Documentation/networking/tuntap.txt)
interfaces. Typically, [`TAP`](https://www.kernel.org/doc/Documentation/networking/tuntap.txt)
interfaces are created for VM connectivity.
To overcome incompatibility between typical container engines expectations
@@ -22,15 +22,15 @@ interfaces with `TAP` ones using [Traffic Control](https://man7.org/linux/man-pa
![Kata Containers networking](../arch-images/network.png)
With a TC filter rules in place, a redirection is created between the container network
and the virtual machine. As an example, the network plugin may place a device,
`eth0`, in the container's network namespace, which is one end of a VETH device.
and the virtual machine. As an example, the network plugin may place a device,
`eth0`, in the container's network namespace, which is one end of a VETH device.
Kata Containers will create a tap device for the VM, `tap0_kata`,
and setup a TC redirection filter to redirect traffic from `eth0`'s ingress to `tap0_kata`'s egress,
and a second TC filter to redirect traffic from `tap0_kata`'s ingress to `eth0`'s egress.
Kata Containers maintains support for MACVTAP, which was an earlier implementation used in Kata.
With this method, Kata created a MACVTAP device to connect directly to the `eth0` device.
TC-filter is the default because it allows for simpler configuration, better CNI plugin
Kata Containers maintains support for MACVTAP, which was an earlier implementation used in Kata.
With this method, Kata created a MACVTAP device to connect directly to the `eth0` device.
TC-filter is the default because it allows for simpler configuration, better CNI plugin
compatibility, and performance on par with MACVTAP.
Kata Containers has deprecated support for bridge due to lacking performance relative to TC-filter and MACVTAP.

View File

@@ -51,7 +51,6 @@ containers started after the VM has been launched.
Users can check to see if the container uses the `devicemapper` block
device as its rootfs by calling `mount(8)` within the container. If
the `devicemapper` block device is used, the root filesystem (`/`)
will be mounted from `/dev/vda`. Users can enable direct mounting of
the underlying block device by setting the runtime
[configuration](README.md#configuration) flag `disable_block_device_use` to
`false`.
will be mounted from `/dev/vda`. Users can disable direct mounting of
the underlying block device through the runtime
[configuration](README.md#configuration).

View File

@@ -111,20 +111,20 @@ In our case, there will be a variety of resources, and every resource has severa
- Are the "service", "message dispatcher" and "runtime handler" all part of the single Kata 3.x runtime binary?
Yes. They are components in Kata 3.x runtime. And they will be packed into one binary.
1. Service is an interface, which is responsible for handling multiple services like task service, image service and etc.
2. Message dispatcher, it is used to match multiple requests from the service module.
3. Runtime handler is used to deal with the operation for sandbox and container.
1. Service is an interface, which is responsible for handling multiple services like task service, image service and etc.
2. Message dispatcher, it is used to match multiple requests from the service module.
3. Runtime handler is used to deal with the operation for sandbox and container.
- What is the name of the Kata 3.x runtime binary?
Apparently we can't use `containerd-shim-v2-kata` because it's already used. We are facing the hardest issue of "naming" again. Any suggestions are welcomed.
Internally we use `containerd-shim-v2-rund`.
- Is the Kata 3.x design compatible with the containerd shimv2 architecture?
- Is the Kata 3.x design compatible with the containerd shimv2 architecture?
Yes. It is designed to follow the functionality of go version kata. And it implements the `containerd shim v2` interface/protocol.
- How will users migrate to the Kata 3.x architecture?
The migration plan will be provided before the Kata 3.x is merging into the main branch.
- Is `Dragonball` limited to its own built-in VMM? Can the `Dragonball` system be configured to work using an external `Dragonball` VMM/hypervisor?
@@ -134,35 +134,35 @@ In our case, there will be a variety of resources, and every resource has severa
`runD` is the `containerd-shim-v2` counterpart of `runC` and can run a pod/containers. `Dragonball` is a `microvm`/VMM that is designed to run container workloads. Instead of `microvm`/VMM, we sometimes refer to it as secure sandbox.
- QEMU, Cloud Hypervisor and Firecracker support are planned, but how that would work. Are they working in separate process?
Yes. They are unable to work as built in VMM.
- What is `upcall`?
The `upcall` is used to hotplug CPU/memory/MMIO devices, and it solves two issues.
1. avoid dependency on PCI/ACPI
2. avoid dependency on `udevd` within guest and get deterministic results for hotplug operations. So `upcall` is an alternative to ACPI based CPU/memory/device hotplug. And we may cooperate with the community to add support for ACPI based CPU/memory/device hotplug if needed.
`Dbs-upcall` is a `vsock-based` direct communication tool between VMM and guests. The server side of the `upcall` is a driver in guest kernel (kernel patches are needed for this feature) and it'll start to serve the requests once the kernel has started. And the client side is in VMM , it'll be a thread that communicates with VSOCK through `uds`. We have accomplished device hotplug / hot-unplug directly through `upcall` in order to avoid virtualization of ACPI to minimize virtual machine's overhead. And there could be many other usage through this direct communication channel. It's already open source.
https://github.com/openanolis/dragonball-sandbox/tree/main/crates/dbs-upcall
https://github.com/openanolis/dragonball-sandbox/tree/main/crates/dbs-upcall
- The URL below says the kernel patches work with 4.19, but do they also work with 5.15+ ?
Forward compatibility should be achievable, we have ported it to 5.10 based kernel.
- Are these patches platform-specific or would they work for any architecture that supports VSOCK?
It's almost platform independent, but some message related to CPU hotplug are platform dependent.
- Could the kernel driver be replaced with a userland daemon in the guest using loopback VSOCK?
We need to create device nodes for hot-added CPU/memory/devices, so it's not easy for userspace daemon to do these tasks.
- The fact that `upcall` allows communication between the VMM and the guest suggests that this architecture might be incompatible with https://github.com/confidential-containers where the VMM should have no knowledge of what happens inside the VM.
1. `TDX` doesn't support CPU/memory hotplug yet.
2. For ACPI based device hotplug, it depends on ACPI `DSDT` table, and the guest kernel will execute `ASL` code to handle during handling those hotplug event. And it should be easier to audit VSOCK based communication than ACPI `ASL` methods.
- What is the security boundary for the monolithic / "Built-in VMM" case?
It has the security boundary of virtualization. More details will be provided in next stage.

View File

@@ -1,62 +1,62 @@
# Motivation
Today, there exist a few gaps between Container Storage Interface (CSI) and virtual machine (VM) based runtimes such as Kata Containers
Today, there exist a few gaps between Container Storage Interface (CSI) and virtual machine (VM) based runtimes such as Kata Containers
that prevent them from working together smoothly.
First, its cumbersome to use a persistent volume (PV) with Kata Containers. Today, for a PV with Filesystem volume mode, Virtio-fs
is the only way to surface it inside a Kata Container guest VM. But often mounting the filesystem (FS) within the guest operating system (OS) is
is the only way to surface it inside a Kata Container guest VM. But often mounting the filesystem (FS) within the guest operating system (OS) is
desired due to performance benefits, availability of native FS features and security benefits over the Virtio-fs mechanism.
Second, its difficult if not impossible to resize a PV online with Kata Containers. While a PV can be expanded on the host OS,
the updated metadata needs to be propagated to the guest OS in order for the application container to use the expanded volume.
Second, its difficult if not impossible to resize a PV online with Kata Containers. While a PV can be expanded on the host OS,
the updated metadata needs to be propagated to the guest OS in order for the application container to use the expanded volume.
Currently, there is not a way to propagate the PV metadata from the host OS to the guest OS without restarting the Pod sandbox.
# Proposed Solution
Because of the OS boundary, these features cannot be implemented in the CSI node driver plugin running on the host OS
as is normally done in the runc container. Instead, they can be done by the Kata Containers agent inside the guest OS,
but it requires the CSI driver to pass the relevant information to the Kata Containers runtime.
An ideal long term solution would be to have the `kubelet` coordinating the communication between the CSI driver and
the container runtime, as described in [KEP-2857](https://github.com/kubernetes/enhancements/pull/2893/files).
Because of the OS boundary, these features cannot be implemented in the CSI node driver plugin running on the host OS
as is normally done in the runc container. Instead, they can be done by the Kata Containers agent inside the guest OS,
but it requires the CSI driver to pass the relevant information to the Kata Containers runtime.
An ideal long term solution would be to have the `kubelet` coordinating the communication between the CSI driver and
the container runtime, as described in [KEP-2857](https://github.com/kubernetes/enhancements/pull/2893/files).
However, as the KEP is still under review, we would like to propose a short/medium term solution to unblock our use case.
The proposed solution is built on top of a previous [proposal](https://github.com/egernst/kata-containers/blob/da-proposal/docs/design/direct-assign-volume.md)
The proposed solution is built on top of a previous [proposal](https://github.com/egernst/kata-containers/blob/da-proposal/docs/design/direct-assign-volume.md)
described by Eric Ernst. The previous proposal has two gaps:
1. Writing a `csiPlugin.json` file to the volume root path introduced a security risk. A malicious user can gain unauthorized
access to a block device by writing their own `csiPlugin.json` to the above location through an ephemeral CSI plugin.
1. Writing a `csiPlugin.json` file to the volume root path introduced a security risk. A malicious user can gain unauthorized
access to a block device by writing their own `csiPlugin.json` to the above location through an ephemeral CSI plugin.
2. The proposal didn't describe how to establish a mapping between a volume and a kata sandbox, which is needed for
2. The proposal didn't describe how to establish a mapping between a volume and a kata sandbox, which is needed for
implementing CSI volume resize and volume stat collection APIs.
This document particularly focuses on how to address these two gaps.
## Assumptions and Limitations
1. The proposal assumes that a block device volume will only be used by one Pod on a node at a time, which we believe
is the most common pattern in Kata Containers use cases. Its also unsafe to have the same block device attached to more than
one Kata pod. In the context of Kubernetes, the `PersistentVolumeClaim` (PVC) needs to have the `accessMode` as `ReadWriteOncePod`.
2. More advanced Kubernetes volume features such as, `fsGroup`, `fsGroupChangePolicy`, and `subPath` are not supported.
1. The proposal assumes that a block device volume will only be used by one Pod on a node at a time, which we believe
is the most common pattern in Kata Containers use cases. Its also unsafe to have the same block device attached to more than
one Kata pod. In the context of Kubernetes, the `PersistentVolumeClaim` (PVC) needs to have the `accessMode` as `ReadWriteOncePod`.
2. More advanced Kubernetes volume features such as, `fsGroup`, `fsGroupChangePolicy`, and `subPath` are not supported.
## End User Interface
1. The user specifies a PV as a direct-assigned volume. How a PV is specified as a direct-assigned volume is left for each CSI implementation to decide.
There are a few options for reference:
1. A storage class parameter specifies whether it's a direct-assigned volume. This avoids any lookups of PVC
or Pod information from the CSI plugin (as external provisioner takes care of these). However, all PVs in the storage class with the parameter set
1. A storage class parameter specifies whether it's a direct-assigned volume. This avoids any lookups of PVC
or Pod information from the CSI plugin (as external provisioner takes care of these). However, all PVs in the storage class with the parameter set
will have host mounts skipped.
2. Use a PVC annotation. This approach requires the CSI plugins have `--extra-create-metadata` [set](https://kubernetes-csi.github.io/docs/external-provisioner.html#persistentvolumeclaim-and-persistentvolume-parameters)
to be able to perform a lookup of the PVC annotations from the API server. Pro: API server lookup of annotations only required during creation of PV.
to be able to perform a lookup of the PVC annotations from the API server. Pro: API server lookup of annotations only required during creation of PV.
Con: The CSI plugin will always skip host mounting of the PV.
3. The CSI plugin can also lookup pod `runtimeclass` during `NodePublish`. This approach can be found in the [ALIBABA CSI plugin](https://github.com/kubernetes-sigs/alibaba-cloud-csi-driver/blob/master/pkg/disk/nodeserver.go#L248).
2. The CSI node driver delegates the direct assigned volume to the Kata Containers runtime. The CSI node driver APIs need to
2. The CSI node driver delegates the direct assigned volume to the Kata Containers runtime. The CSI node driver APIs need to
be modified to pass the volume mount information and collect volume information to/from the Kata Containers runtime by invoking `kata-runtime` command line commands.
* **`NodePublishVolume`** -- It invokes `kata-runtime direct-volume add --volume-path [volumePath] --mount-info [mountInfo]`
* **NodePublishVolume** -- It invokes `kata-runtime direct-volume add --volume-path [volumePath] --mount-info [mountInfo]`
to propagate the volume mount information to the Kata Containers runtime for it to carry out the filesystem mount operation.
The `volumePath` is the [target_path](https://github.com/container-storage-interface/spec/blob/master/csi.proto#L1364) in the CSI `NodePublishVolumeRequest`.
The `mountInfo` is a serialized JSON string.
* **`NodeGetVolumeStats`** -- It invokes `kata-runtime direct-volume stats --volume-path [volumePath]` to retrieve the filesystem stats of direct-assigned volume.
* **`NodeExpandVolume`** -- It invokes `kata-runtime direct-volume resize --volume-path [volumePath] --size [size]` to send a resize request to the Kata Containers runtime to
The `mountInfo` is a serialized JSON string.
* **NodeGetVolumeStats** -- It invokes `kata-runtime direct-volume stats --volume-path [volumePath]` to retrieve the filesystem stats of direct-assigned volume.
* **NodeExpandVolume** -- It invokes `kata-runtime direct-volume resize --volume-path [volumePath] --size [size]` to send a resize request to the Kata Containers runtime to
resize the direct-assigned volume.
* **`NodeStageVolume/NodeUnStageVolume`** -- It invokes `kata-runtime direct-volume remove --volume-path [volumePath]` to remove the persisted metadata of a direct-assigned volume.
* **NodeStageVolume/NodeUnStageVolume** -- It invokes `kata-runtime direct-volume remove --volume-path [volumePath]` to remove the persisted metadata of a direct-assigned volume.
The `mountInfo` object is defined as follows:
```Golang
@@ -78,17 +78,17 @@ Notes: given that the `mountInfo` is persisted to the disk by the Kata runtime,
## Implementation Details
### Kata runtime
Instead of the CSI node driver writing the mount info into a `csiPlugin.json` file under the volume root,
as described in the original proposal, here we propose that the CSI node driver passes the mount information to
the Kata Containers runtime through a new `kata-runtime` commandline command. The `kata-runtime` then writes the mount
Instead of the CSI node driver writing the mount info into a `csiPlugin.json` file under the volume root,
as described in the original proposal, here we propose that the CSI node driver passes the mount information to
the Kata Containers runtime through a new `kata-runtime` commandline command. The `kata-runtime` then writes the mount
information to a `mountInfo.json` file in a predefined location (`/run/kata-containers/shared/direct-volumes/[volume_path]/`).
When the Kata Containers runtime starts a container, it verifies whether a volume mount is a direct-assigned volume by checking
whether there is a `mountInfo` file under the computed Kata `direct-volumes` directory. If it is, the runtime parses the `mountInfo` file,
When the Kata Containers runtime starts a container, it verifies whether a volume mount is a direct-assigned volume by checking
whether there is a `mountInfo` file under the computed Kata `direct-volumes` directory. If it is, the runtime parses the `mountInfo` file,
updates the mount spec with the data in `mountInfo`. The updated mount spec is then passed to the Kata agent in the guest VM together
with other mounts. The Kata Containers runtime also creates a file named by the sandbox id under the `direct-volumes/[volume_path]/`
directory. The reason for adding a sandbox id file is to establish a mapping between the volume and the sandbox using it.
Later, when the Kata Containers runtime handles the `get-stats` and `resize` commands, it uses the sandbox id to identify
with other mounts. The Kata Containers runtime also creates a file named by the sandbox id under the `direct-volumes/[volume_path]/`
directory. The reason for adding a sandbox id file is to establish a mapping between the volume and the sandbox using it.
Later, when the Kata Containers runtime handles the `get-stats` and `resize` commands, it uses the sandbox id to identify
the endpoint of the corresponding `containerd-shim-kata-v2`.
### containerd-shim-kata-v2 changes
@@ -101,12 +101,12 @@ $ curl --unix-socket "$shim_socket_path" -I -X GET 'http://localhost/direct-volu
$ curl --unix-socket "$shim_socket_path" -I -X POST 'http://localhost/direct-volume/resize' -d '{ "volumePath"": [volumePath], "Size": "123123" }'
```
The shim then forwards the corresponding request to the `kata-agent` to carry out the operations inside the guest VM. For `resize` operation,
the Kata runtime also needs to notify the hypervisor to resize the block device (e.g. call `block_resize` in QEMU).
The shim then forwards the corresponding request to the `kata-agent` to carry out the operations inside the guest VM. For `resize` operation,
the Kata runtime also needs to notify the hypervisor to resize the block device (e.g. call `block_resize` in QEMU).
### Kata agent changes
The mount spec of a direct-assigned volume is passed to `kata-agent` through the existing `Storage` GRPC object.
The mount spec of a direct-assigned volume is passed to `kata-agent` through the existing `Storage` GRPC object.
Two new APIs and three new GRPC objects are added to GRPC protocol between the shim and agent for resizing and getting volume stats:
```protobuf
@@ -226,7 +226,7 @@ Lets assume that changes have been made in the `aws-ebs-csi-driver` node driv
1. In the node CSI driver, the `NodePublishVolume` API invokes: `kata-runtime direct-volume add --volume-path "/kubelet/a/b/c/d/sdf" --mount-info "{\"Device\": \"/dev/sdf\", \"fstype\": \"ext4\"}"`.
2. The `Kata-runtime` writes the mount-info JSON to a file called `mountInfo.json` under `/run/kata-containers/shared/direct-volumes/kubelet/a/b/c/d/sdf`.
**Node `unstage` volume**
**Node unstage volume**
1. In the node CSI driver, the `NodeUnstageVolume` API invokes: `kata-runtime direct-volume remove --volume-path "/kubelet/a/b/c/d/sdf"`.
2. Kata-runtime deletes the directory `/run/kata-containers/shared/direct-volumes/kubelet/a/b/c/d/sdf`.

View File

@@ -59,5 +59,5 @@ The table below summarized when and where those different hooks will be executed
+ `Hook Path` specifies where hook's path be resolved.
+ `Exec Place` specifies in which namespace those hooks can be executed.
+ For `CreateContainer` Hooks, OCI requires to run them inside the container namespace while the hook executable path is in the host runtime, which is a non-starter for VM-based containers. So we design to keep them running in the *host vmm namespace.*
+ `Exec Time` specifies at which time point those hooks can be executed.
+ For `CreateContainer` Hooks, OCI requires to run them inside the container namespace while the hook executable path is in the host runtime, which is a non-starter for VM-based containers. So we design to keep them running in the *host vmm namespace.*
+ `Exec Time` specifies at which time point those hooks can be executed.

View File

@@ -118,7 +118,7 @@ all vCPU and I/O related threads) will be created in the `/kata_<PodSandboxID>`
### Why create a kata-cgroup under the parent cgroup?
And why not directly adding the per sandbox shim directly to the pod cgroup (e.g.
And why not directly adding the per sandbox shim directly to the pod cgroup (e.g.
`/kubepods` in the Kubernetes context)?
The Kata Containers shim implementation creates a per-sandbox cgroup
@@ -219,13 +219,13 @@ the `/kubepods` cgroup hierarchy, and a `/<PodSandboxID>` under the `/kata_overh
On a typical cgroup v1 hierarchy mounted under `/sys/fs/cgroup/`, for a pod which sandbox
ID is `12345678`, create with `sandbox_cgroup_only` disabled, the 2 memory subsystems
for the sandbox cgroup and the overhead cgroup would respectively live under
for the sandbox cgroup and the overhead cgroup would respectively live under
`/sys/fs/cgroup/memory/kubepods/kata_12345678` and `/sys/fs/cgroup/memory/kata_overhead/12345678`.
Unlike when `sandbox_cgroup_only` is enabled, the Kata Containers shim will move itself
to the overhead cgroup first, and then move the vCPU threads to the sandbox cgroup as
they're created. All Kata processes and threads will run under the overhead cgroup except for
the vCPU threads.
the vCPU threads.
With `sandbox_cgroup_only` disabled, Kata Containers assumes the pod cgroup is only sized
to accommodate for the actual container workloads processes. For Kata, this maps
@@ -247,7 +247,7 @@ cgroup size and constraints accordingly.
# Supported cgroups
Kata Containers currently supports cgroups `v1` and `v2`.
Kata Containers currently supports cgroups `v1` and `v2`.
In the following sections each cgroup is described briefly.

View File

@@ -119,17 +119,17 @@ The metrics service also doesn't hold any metrics in memory.
*Metrics size*: response size of one Prometheus scrape request.
It's easy to estimate the size of one metrics fetch request issued by Prometheus.
The formula to calculate the expected size when no gzip compression is in place is:
The formula to calculate the expected size when no gzip compression is in place is:
9 + (144 - 9) * `number of kata sandboxes`
Prometheus supports `gzip compression`. When enabled, the response size of each request will be smaller:
Prometheus supports `gzip compression`. When enabled, the response size of each request will be smaller:
2 + (10 - 2) * `number of kata sandboxes`
**Example**
We have 10 sandboxes running on a node. The expected size of one metrics fetch request issued by Prometheus against the kata-monitor agent running on that node will be:
**Example**
We have 10 sandboxes running on a node. The expected size of one metrics fetch request issued by Prometheus against the kata-monitor agent running on that node will be:
9 + (144 - 9) * 10 = **1.35M**
If `gzip compression` is enabled:
If `gzip compression` is enabled:
2 + (10 - 2) * 10 = **82K**
#### Metrics delay ####

View File

@@ -43,7 +43,7 @@ To fulfill the [Kata design requirements](kata-design-requirements.md), and base
|`sandbox.AddInterface(inf)`| Add new NIC to the sandbox.|
|`sandbox.RemoveInterface(inf)`| Remove a NIC from the sandbox.|
|`sandbox.ListInterfaces()`| List all NICs and their configurations in the sandbox, return a `pbTypes.Interface` list.|
|`sandbox.UpdateRoutes(routes)`| Update the sandbox route table (e.g. for port mapping support), return a `pbTypes.Route` list.|
|`sandbox.UpdateRoutes(routes)`| Update the sandbox route table (e.g. for portmapping support), return a `pbTypes.Route` list.|
|`sandbox.ListRoutes()`| List the sandbox route table, return a `pbTypes.Route` list.|
### Sandbox Relay API

View File

@@ -71,7 +71,7 @@ The Kata Containers runtime **MUST** support scalable I/O through the SRIOV tech
### Virtualization overhead reduction
A compelling aspect of containers is their minimal overhead compared to bare metal applications.
A container runtime should keep the overhead to a minimum in order to provide the expected user
experience.
experience.
The Kata Containers runtime implementation **SHOULD** be optimized for:
* Minimal workload boot and shutdown times

View File

@@ -5,7 +5,7 @@ To safeguard the integrity of container images and prevent tampering from the ho
## Introduction to remote snapshot
Containerd 1.7 introduced `remote snapshotter` feature which is the foundation for pulling images in the guest for Confidential Containers.
While it's beyond the scope of this document to fully explain how the container rootfs is created to the point it can be executed, a fundamental grasp of the snapshot concept is essential. Putting it in a simple way, containerd fetches the image layers from an OCI registry into its local content storage. However, they cannot be mounted as is (e.g. the layer can be tar+gzip compressed) as well as they should be immutable so the content can be shared among containers. Thus containerd leverages snapshots of those layers to build the container's rootfs.
While it's beyond the scope of this document to fully explain how the container rootfs is created to the point it can be executed, a fundamental grasp of the snapshot concept is essential. Putting it in a simple way, containerd fetches the image layers from an OCI registry into its local content storage. However, they cannot be mounted as is (e.g. the layer can be tar+gzip compressed) as well as they should be immutable so the content can be shared among containers. Thus containerd leverages snapshots of those layers to build the container's rootfs.
The role of `remote snapshotter` is to reuse snapshots that are stored in a remotely shared place, thus enabling containerd to prepare the containers rootfs in a manner similar to that of a local `snapshotter`. The key behavior that makes this the building block of Kata's guest image management for Confidential Containers is that containerd will not pull the image layers from registry, instead it assumes that `remote snapshotter` and/or an external entity will perform that operation on his behalf.
@@ -48,7 +48,7 @@ Pull the container image directly from the guest VM using `nydus snapshotter` ba
#### Architecture
The following diagram provides an overview of the architecture for pulling image in the guest with key components.
The following diagram provides an overview of the architecture for pulling image in the guest with key components.
```mermaid
flowchart LR
Kubelet[kubelet]--> |1\. Pull image request & metadata|Containerd
@@ -129,7 +129,7 @@ Next the `handleImageGuestPullBlockVolume()` is called to build the Storage obje
Below is an example of storage information packaged in the message sent to the kata-agent:
```json
"driver": "image_guest_pull",
"driver": "image_guest_pull",
"driver_options": [
"image_guest_pull"{
"metadata":{
@@ -145,15 +145,15 @@ Below is an example of storage information packaged in the message sent to the k
"io.kubernetes.cri.sandbox-uid": "de7c6a0c-79c0-44dc-a099-69bb39f180af",
}
}
],
"source": "quay.io/kata-containers/confidential-containers:unsigned",
"fstype": "overlay",
"options": [],
],
"source": "quay.io/kata-containers/confidential-containers:unsigned",
"fstype": "overlay",
"options": [],
"mount_point": "/run/kata-containers/cb0b47276ea66ee9f44cc53afa94d7980b57a52c3f306f68cb034e58d9fbd3c6/rootfs",
```
Next, the kata-agent's RPC module will handle the create container request which, among other things, involves adding storages to the sandbox. The storage module contains implementations of `StorageHandler` interface for various storage types, being the `ImagePullHandler` in charge of handling the storage object for the container image (the storage manager instantiates the handler based on the value of the "driver").
`ImagePullHandler` delegates the image pulling operation to the `confidential_data_hub.pull_image()` that is going to create the image's bundle directory on the guest filesystem and, in turn, the `ImagePullService` of Confidential Data Hub to fetch, uncompress and mount the image's rootfs.
`ImagePullHandler` delegates the image pulling operation to the `confidential_data_hub.pull_image()` that is going to create the image's bundle directory on the guest filesystem and, in turn, the `ImagePullService` of Confidential Data Hub to fetch, uncompress and mount the image's rootfs.
> **Notes:**
> In this flow, `confidential_data_hub.pull_image()` parses the image metadata, looking for either the `io.kubernetes.cri.container-type: sandbox` or `io.kubernetes.cri-o.ContainerType: sandbox` (CRI-IO case) annotation, then it never calls the `pull_image()` RPC of Confidential Data Hub because the pause image is expected to already be inside the guest's filesystem, so instead `confidential_data_hub.unpack_pause_image()` is called.

View File

@@ -8,7 +8,7 @@ The following benchmarking result shows the performance improvement compared wit
## Proposal - Bring `lazyload` ability to Kata Containers
`Nydusd` is a fuse/`virtiofs` daemon which is provided by `nydus` project and it supports `PassthroughFS` and [`rafs`](https://github.com/dragonflyoss/image-service/blob/master/docs/nydus-design.md) (Registry Acceleration File System) natively, so in Kata Containers, we can use `nydusd` in place of `virtiofsd` and mount `nydus` image to guest in the meanwhile.
`Nydusd` is a fuse/`virtiofs` daemon which is provided by `nydus` project and it supports `PassthroughFS` and [RAFS](https://github.com/dragonflyoss/image-service/blob/master/docs/nydus-design.md) (Registry Acceleration File System) natively, so in Kata Containers, we can use `nydusd` in place of `virtiofsd` and mount `nydus` image to guest in the meanwhile.
The process of creating/starting Kata Containers with `virtiofsd`,

View File

@@ -1,6 +1,6 @@
# Virtual machine vCPU sizing in Kata Containers 3.0
> Preview:
> Preview:
> [Kubernetes(since 1.23)][1] and [Containerd(since 1.6.0-beta4)][2] will help calculate `Sandbox Size` info and pass it to Kata Containers through annotations.
> In order to adapt to this beneficial change and be compatible with the past, we have implemented the new vCPUs handling way in `runtime-rs`, which is slightly different from the original `runtime-go`'s design.
@@ -20,7 +20,7 @@ Our understanding and priority of these resources are as follows, which will aff
* `default_vcpus`: default number of vCPUs when starting a VM.
* `default_maxvcpus`: maximum number of vCPUs.
* From `Annotation`:
* `InitialSize`: we call the size of the resource passed from the annotations as `InitialSize`. Kubernetes will calculate the sandbox size according to the Pod's statement, which is the `InitialSize` here. This size should be the size we want to prioritize.
* `InitialSize`: we call the size of the resource passed from the annotations as `InitialSize`. Kubernetes will calculate the sandbox size according to the Pod's statement, which is the `InitialSize` here. This size should be the size we want to prioritize.
* From `Container Spec`:
* The amount of CPU resources that the Container wants to use will be declared through the spec. Including the aforementioned annotations, we mainly consider `cpu quota` and `cpuset` when calculating the number of vCPUs.
* `cpu quota`: `cpu quota` is the most common way to declare the amount of CPU resources. The number of vCPUs introduced by `cpu quota` declared in a container's spec is: `vCPUs = ceiling( quota / period )`.

View File

@@ -1,9 +1,9 @@
# Design Doc for Kata Containers VCPUs Pinning Feature
# Design Doc for Kata Containers' VCPUs Pinning Feature
## Background
By now, vCPU threads of Kata Containers are scheduled randomly to CPUs. And each pod would request a specific set of CPUs which we call it CPU set (just the CPU set meaning in Linux cgroups).
By now, vCPU threads of Kata Containers are scheduled randomly to CPUs. And each pod would request a specific set of CPUs which we call it CPU set (just the CPU set meaning in Linux cgroups).
If the number of vCPU threads are equal to that of CPUs claimed in CPU set, we can then pin each vCPU thread to one specified CPU, to reduce the cost of random scheduling.
If the number of vCPU threads are equal to that of CPUs claimed in CPU set, we can then pin each vCPU thread to one specified CPU, to reduce the cost of random scheduling.
## Detailed Design
@@ -20,7 +20,7 @@ Two ways are provided to use this vCPU thread pinning feature: through `QEMU` co
### When is VCPUs Pinning Checked?
As shown in Section 1, when `num(vCPU threads) == num(CPUs in CPU set)`, we shall pin each vCPU thread to a specified CPU. And when this condition is broken, we should restore to the original random scheduling pattern.
As shown in Section 1, when `num(vCPU threads) == num(CPUs in CPU set)`, we shall pin each vCPU thread to a specified CPU. And when this condition is broken, we should restore to the original random scheduling pattern.
So when may `num(CPUs in CPU set)` change? There are 5 possible scenes:
| Possible scenes | Related Code |
@@ -34,4 +34,4 @@ So when may `num(CPUs in CPU set)` change? There are 5 possible scenes:
### Core Pinning Logics
We can split the whole process into the following steps. Related methods are `checkVCPUsPinning` and `resetVCPUsPinning`, in file Sandbox.go.
![](arch-images/vcpus-pinning-process.png)
![](arch-images/vcpus-pinning-process.png)

View File

@@ -1,264 +0,0 @@
# Helm Configuration
## Parameters
The helm chart provides a comprehensive set of configuration options. You may view the parameters and their descriptions by going to the [GitHub source](https://github.com/kata-containers/kata-containers/blob/main/tools/packaging/kata-deploy/helm-chart/kata-deploy/values.yaml) or by using helm:
```sh
# List available kata-deploy chart versions:
# helm search repo kata-deploy-charts/kata-deploy --versions
#
# Then replace X.Y.Z below with the desired chart version:
helm show values --version X.Y.Z oci://ghcr.io/kata-containers/kata-deploy-charts/kata-deploy
```
### shims
Kata ships with a number of pre-built artifacts and runtimes. You may selectively enable or disable specific shims. For example:
```yaml title="values.yaml"
shims:
disableAll: true
qemu:
enabled: true
qemu-nvidia-gpu:
enabled: true
qemu-nvidia-gpu-snp:
enabled: false
```
Shims can also have configuration options specific to them:
```yaml
qemu-nvidia-gpu:
enabled: ~
supportedArches:
- amd64
- arm64
allowedHypervisorAnnotations: []
containerd:
snapshotter: ""
runtimeClass:
# This label is automatically added by gpu-operator. Override it
# if you want to use a different label.
# Uncomment once GPU Operator v26.3 is out
# nodeSelector:
# nvidia.com/cc.ready.state: "false"
```
It's best to reference the default `values.yaml` file above for more details.
### Custom Runtimes
Kata allows you to create custom runtime configurations. This is done by overlaying one of the pre-existing runtime configs with user-provided configs. For example, we can use the `qemu-nvidia-gpu` as a base config and overlay our own parameters to it:
```yaml
customRuntimes:
enabled: false
runtimes:
my-gpu-runtime:
baseConfig: "qemu-nvidia-gpu" # Required: existing config to use as base
dropIn: | # Optional: overrides via config.d mechanism
[hypervisor.qemu]
default_memory = 1024
default_vcpus = 4
runtimeClass: |
kind: RuntimeClass
apiVersion: node.k8s.io/v1
metadata:
name: kata-my-gpu-runtime
labels:
app.kubernetes.io/managed-by: kata-deploy
handler: kata-my-gpu-runtime
overhead:
podFixed:
memory: "640Mi"
cpu: "500m"
scheduling:
nodeSelector:
katacontainers.io/kata-runtime: "true"
# Optional: CRI-specific configuration
containerd:
snapshotter: "nydus" # Configure containerd snapshotter (nydus, erofs, etc.)
crio:
pullType: "guest-pull" # Configure CRI-O runtime_pull_image = true
```
Again, view the default [`values.yaml`](#parameters) file for more details.
## Examples
We provide a few examples that you can pass to helm via the `-f`/`--values` flag.
### [`try-kata-tee.values.yaml`](https://github.com/kata-containers/kata-containers/blob/main/tools/packaging/kata-deploy/helm-chart/kata-deploy/try-kata-tee.values.yaml)
This file enables only the TEE (Trusted Execution Environment) shims for confidential computing:
```sh
helm install kata-deploy oci://ghcr.io/kata-containers/kata-deploy-charts/kata-deploy \
--version VERSION \
-f try-kata-tee.values.yaml
```
Includes:
- `qemu-snp` - AMD SEV-SNP (amd64)
- `qemu-tdx` - Intel TDX (amd64)
- `qemu-se` - IBM Secure Execution for Linux (SEL) (s390x)
- `qemu-se-runtime-rs` - IBM Secure Execution for Linux (SEL) Rust runtime (s390x)
- `qemu-cca` - Arm Confidential Compute Architecture (arm64)
- `qemu-coco-dev` - Confidential Containers development (amd64, s390x)
- `qemu-coco-dev-runtime-rs` - Confidential Containers development Rust runtime (amd64, s390x)
### [`try-kata-nvidia-gpu.values.yaml`](https://github.com/kata-containers/kata-containers/blob/main/tools/packaging/kata-deploy/helm-chart/kata-deploy/try-kata-nvidia-gpu.values.yaml)
This file enables only the NVIDIA GPU-enabled shims:
```sh
helm install kata-deploy oci://ghcr.io/kata-containers/kata-deploy-charts/kata-deploy \
--version VERSION \
-f try-kata-nvidia-gpu.values.yaml
```
Includes:
- `qemu-nvidia-gpu` - Standard NVIDIA GPU support (amd64, arm64)
- `qemu-nvidia-gpu-snp` - NVIDIA GPU with AMD SEV-SNP (amd64)
- `qemu-nvidia-gpu-tdx` - NVIDIA GPU with Intel TDX (amd64)
### `nodeSelector`
We can deploy Kata only to specific nodes using `nodeSelector`
```sh
# First, label the nodes where you want kata-containers to be installed
$ kubectl label nodes worker-node-1 kata-containers=enabled
$ kubectl label nodes worker-node-2 kata-containers=enabled
# Then install the chart with `nodeSelector`
$ helm install kata-deploy \
--set nodeSelector.kata-containers="enabled" \
"${CHART}" --version "${VERSION}"
```
You can also use a values file:
```yaml title="values.yaml"
nodeSelector:
kata-containers: "enabled"
node-type: "worker"
```
```sh
$ helm install kata-deploy -f values.yaml "${CHART}" --version "${VERSION}"
```
### Multiple Kata installations on the Same Node
For debugging, testing and other use-case it is possible to deploy multiple
versions of Kata on the very same node. All the needed artifacts are getting the
`multiInstallSuffix` appended to distinguish each installation. **BEWARE** that one
needs at least **containerd-2.0** since this version has drop-in conf support
which is a prerequisite for the `multiInstallSuffix` to work properly.
```sh
$ helm install kata-deploy-cicd \
-n kata-deploy-cicd \
--set env.multiInstallSuffix=cicd \
--set env.debug=true \
"${CHART}" --version "${VERSION}"
```
Note: `runtimeClasses` are automatically created by Helm (via
`runtimeClasses.enabled=true`, which is the default).
Now verify the installation by examining the `runtimeClasses`:
```sh
$ kubectl get runtimeClasses
NAME HANDLER AGE
kata-clh-cicd kata-clh-cicd 77s
kata-cloud-hypervisor-cicd kata-cloud-hypervisor-cicd 77s
kata-dragonball-cicd kata-dragonball-cicd 77s
kata-fc-cicd kata-fc-cicd 77s
kata-qemu-cicd kata-qemu-cicd 77s
kata-qemu-coco-dev-cicd kata-qemu-coco-dev-cicd 77s
kata-qemu-nvidia-gpu-cicd kata-qemu-nvidia-gpu-cicd 77s
kata-qemu-nvidia-gpu-snp-cicd kata-qemu-nvidia-gpu-snp-cicd 77s
kata-qemu-nvidia-gpu-tdx-cicd kata-qemu-nvidia-gpu-tdx-cicd 76s
kata-qemu-runtime-rs-cicd kata-qemu-runtime-rs-cicd 77s
kata-qemu-se-runtime-rs-cicd kata-qemu-se-runtime-rs-cicd 77s
kata-qemu-snp-cicd kata-qemu-snp-cicd 77s
kata-qemu-tdx-cicd kata-qemu-tdx-cicd 77s
kata-stratovirt-cicd kata-stratovirt-cicd 77s
```
## RuntimeClass Node Selectors for TEE Shims
**Manual configuration:** Any `nodeSelector` you set under `shims.<shim>.runtimeClass.nodeSelector`
is **always applied** to that shim's RuntimeClass, whether or not NFD is present. Use this when
you want to pin TEE workloads to specific nodes (e.g. without NFD, or with custom labels).
**Auto-inject when NFD is present:** If you do *not* set a `runtimeClass.nodeSelector` for a
TEE shim, the chart can **automatically inject** NFD-based labels when NFD is detected in the
cluster (deployed by this chart with `node-feature-discovery.enabled=true` or found externally):
- AMD SEV-SNP shims: `amd.feature.node.kubernetes.io/snp: "true"`
- Intel TDX shims: `intel.feature.node.kubernetes.io/tdx: "true"`
- IBM Secure Execution for Linux (SEL) shims (s390x): `feature.node.kubernetes.io/cpu-security.se.enabled: "true"`
The chart uses Helm's `lookup` function to detect NFD (by looking for the
`node-feature-discovery-worker` DaemonSet). Auto-inject only runs when NFD is detected and
no manual `runtimeClass.nodeSelector` is set for that shim.
**Note**: NFD detection requires cluster access. During `helm template` (dry-run without a
cluster), external NFD is not seen, so auto-injected labels are not added. Manual
`runtimeClass.nodeSelector` values are still applied in all cases.
## Customizing Configuration with Drop-in Files
When kata-deploy installs Kata Containers, the base configuration files should not
be modified directly. Instead, use drop-in configuration files to customize
settings. This approach ensures your customizations survive kata-deploy upgrades.
### How Drop-in Files Work
The Kata runtime reads the base configuration file and then applies any `.toml`
files found in the `config.d/` directory alongside it. Files are processed in
alphabetical order, with later files overriding earlier settings.
### Creating Custom Drop-in Files
To add custom settings, create a `.toml` file in the appropriate `config.d/`
directory. Use a numeric prefix to control the order of application.
**Reserved prefixes** (used by kata-deploy):
- `10-*`: Core kata-deploy settings
- `20-*`: Debug settings
- `30-*`: Kernel parameters
**Recommended prefixes for custom settings**: `50-89`
### Drop-In Config Examples
#### Adding Custom Kernel Parameters
```bash
# SSH into the node or use kubectl exec
sudo mkdir -p /opt/kata/share/defaults/kata-containers/runtimes/qemu/config.d/
sudo cat > /opt/kata/share/defaults/kata-containers/runtimes/qemu/config.d/50-custom.toml << 'EOF'
[hypervisor.qemu]
kernel_params = "my_param=value"
EOF
```
#### Changing Default Memory Size
```bash
sudo cat > /opt/kata/share/defaults/kata-containers/runtimes/qemu/config.d/50-memory.toml << 'EOF'
[hypervisor.qemu]
default_memory = 4096
EOF
```

View File

@@ -49,4 +49,4 @@
- [How to use the Kata Agent Policy](how-to-use-the-kata-agent-policy.md)
- [How to pull images in the guest](how-to-pull-images-in-guest-with-kata.md)
- [How to use mem-agent to decrease the memory usage of Kata container](how-to-use-memory-agent.md)
- [How to use seccomp with runtime-rs](how-to-use-seccomp-with-runtime-rs.md)
- [How to use seccomp with runtime-rs](how-to-use-seccomp-with-runtime-rs.md)

View File

@@ -1,29 +1,29 @@
# How to use Kata Containers and Containerd
This document covers the installation and configuration of [containerd](https://containerd.io/)
This document covers the installation and configuration of [containerd](https://containerd.io/)
and [Kata Containers](https://katacontainers.io). The containerd provides not only the `ctr`
command line tool, but also the [CRI](https://kubernetes.io/blog/2016/12/container-runtime-interface-cri-in-kubernetes/)
command line tool, but also the [CRI](https://kubernetes.io/blog/2016/12/container-runtime-interface-cri-in-kubernetes/)
interface for [Kubernetes](https://kubernetes.io) and other CRI clients.
This document is primarily written for Kata Containers v1.5.0-rc2 or above, and containerd v1.2.0 or above.
This document is primarily written for Kata Containers v1.5.0-rc2 or above, and containerd v1.2.0 or above.
Previous versions are addressed here, but we suggest users upgrade to the newer versions for better support.
## Concepts
### Kubernetes `RuntimeClass`
[`RuntimeClass`](https://kubernetes.io/docs/concepts/containers/runtime-class/) is a Kubernetes feature first
introduced in Kubernetes 1.12 as alpha. It is the feature for selecting the container runtime configuration to
[`RuntimeClass`](https://kubernetes.io/docs/concepts/containers/runtime-class/) is a Kubernetes feature first
introduced in Kubernetes 1.12 as alpha. It is the feature for selecting the container runtime configuration to
use to run a pods containers. This feature is supported in `containerd` since [v1.2.0](https://github.com/containerd/containerd/releases/tag/v1.2.0).
Before the `RuntimeClass` was introduced, Kubernetes was not aware of the difference of runtimes on the node. `kubelet`
creates Pod sandboxes and containers through CRI implementations, and treats all the Pods equally. However, there
are requirements to run trusted Pods (i.e. Kubernetes plugin) in a native container like runc, and to run untrusted
are requirements to run trusted Pods (i.e. Kubernetes plugin) in a native container like runc, and to run untrusted
workloads with isolated sandboxes (i.e. Kata Containers).
As a result, the CRI implementations extended their semantics for the requirements:
- At the beginning, [`Frakti`](https://github.com/kubernetes/frakti) checks the network configuration of a Pod, and
- At the beginning, [Frakti](https://github.com/kubernetes/frakti) checks the network configuration of a Pod, and
treat Pod with `host` network as trusted, while others are treated as untrusted.
- The containerd introduced an annotation for untrusted Pods since [v1.0](https://github.com/containerd/cri/blob/v1.0.0-rc.0/docs/config.md):
```yaml
@@ -32,17 +32,17 @@ As a result, the CRI implementations extended their semantics for the requiremen
```
- Similarly, CRI-O introduced the annotation `io.kubernetes.cri-o.TrustedSandbox` for untrusted Pods.
To eliminate the complexity of user configuration introduced by the non-standardized annotations and provide
extensibility, `RuntimeClass` was introduced. This gives users the ability to affect the runtime behavior
through `RuntimeClass` without the knowledge of the CRI daemons. We suggest that users with multiple runtimes
To eliminate the complexity of user configuration introduced by the non-standardized annotations and provide
extensibility, `RuntimeClass` was introduced. This gives users the ability to affect the runtime behavior
through `RuntimeClass` without the knowledge of the CRI daemons. We suggest that users with multiple runtimes
use `RuntimeClass` instead of the deprecated annotations.
### Containerd Runtime V2 API: Shim V2 API
The [`containerd-shim-kata-v2` (short as `shimv2` in this documentation)](../../src/runtime/cmd/containerd-shim-kata-v2/)
implements the [Containerd Runtime V2 (Shim API)](https://github.com/containerd/containerd/tree/main/core/runtime/v2) for Kata.
With `shimv2`, Kubernetes can launch Pod and OCI-compatible containers with one shim per Pod. Prior to `shimv2`, `2N+1`
shims (i.e. a `containerd-shim` and a `kata-shim` for each container and the Pod sandbox itself) and no standalone `kata-proxy`
With `shimv2`, Kubernetes can launch Pod and OCI-compatible containers with one shim per Pod. Prior to `shimv2`, `2N+1`
shims (i.e. a `containerd-shim` and a `kata-shim` for each container and the Pod sandbox itself) and no standalone `kata-proxy`
process were used, even with VSOCK not available.
![Kubernetes integration with shimv2](../design/arch-images/shimv2.svg)
@@ -87,7 +87,7 @@ $ popd
### Install `cri-tools`
> **Note:** `cri-tools` is a set of tools for CRI used for development and testing. Users who only want
> **Note:** `cri-tools` is a set of tools for CRI used for development and testing. Users who only want
> to use containerd with Kubernetes can skip the `cri-tools`.
You can install the `cri-tools` from source code:
@@ -104,7 +104,7 @@ $ popd
### Configure containerd to use Kata Containers
By default, the configuration of containerd is located at `/etc/containerd/config.toml`, and the
By default, the configuration of containerd is located at `/etc/containerd/config.toml`, and the
`cri` plugins are placed in the following section:
```toml
@@ -123,7 +123,7 @@ The following sections outline how to add Kata Containers to the configurations.
#### Kata Containers as a `RuntimeClass`
For
For
- Kata Containers v1.5.0 or above (including `1.5.0-rc`)
- Containerd v1.2.0 or above
- Kubernetes v1.12.0 or above
@@ -132,8 +132,8 @@ The `RuntimeClass` is suggested.
The following configuration includes two runtime classes:
- `plugins.cri.containerd.runtimes.runc`: the runc, and it is the default runtime.
- `plugins.cri.containerd.runtimes.kata`: The function in containerd (reference [the document here](https://github.com/containerd/containerd/tree/main/core/runtime/v2))
where the dot-connected string `io.containerd.kata.v2` is translated to `containerd-shim-kata-v2` (i.e. the
- `plugins.cri.containerd.runtimes.kata`: The function in containerd (reference [the document here](https://github.com/containerd/containerd/tree/main/core/runtime/v2))
where the dot-connected string `io.containerd.kata.v2` is translated to `containerd-shim-kata-v2` (i.e. the
binary name of the Kata implementation of [Containerd Runtime V2 (Shim API)](https://github.com/containerd/containerd/tree/main/core/runtime/v2)).
```toml
@@ -168,9 +168,9 @@ This `ConfigPath` option is optional. If you do not specify it, shimv2 first tri
#### Kata Containers as the runtime for untrusted workload
For cases without `RuntimeClass` support, we can use the legacy annotation method to support using Kata Containers
for an untrusted workload. With the following configuration, you can run trusted workloads with a runtime such as `runc`
and then, run an untrusted workload with Kata Containers:
For cases without `RuntimeClass` support, we can use the legacy annotation method to support using Kata Containers
for an untrusted workload. With the following configuration, you can run trusted workloads with a runtime such as `runc`
and then, run an untrusted workload with Kata Containers:
```toml
[plugins.cri.containerd]
@@ -201,9 +201,9 @@ If you want to set Kata Containers as the only runtime in the deployment, you ca
> **Note:** If you skipped the [Install `cri-tools`](#install-cri-tools) section, you can skip this section too.
First, add the CNI configuration in the containerd configuration.
First, add the CNI configuration in the containerd configuration.
The following is the configuration if you installed CNI as the *[Install CNI plugins](#install-cni-plugins)* section outlined.
The following is the configuration if you installed CNI as the *[Install CNI plugins](#install-cni-plugins)* section outlined.
Put the CNI configuration as `/etc/cni/net.d/10-mynet.conf`:
@@ -324,7 +324,7 @@ $ sudo crictl start 1aab7585530e6
1aab7585530e6
```
In Kubernetes, you need to create a `RuntimeClass` resource and add the `RuntimeClass` field in the Pod Spec
In Kubernetes, you need to create a `RuntimeClass` resource and add the `RuntimeClass` field in the Pod Spec
(see this [document](https://kubernetes.io/docs/concepts/containers/runtime-class/) for more information).
If `RuntimeClass` is not supported, you can use the following annotation in a Kubernetes pod to identify as an untrusted workload:

View File

@@ -3358,4 +3358,4 @@
"title": "Kata containers",
"uid": "75pdqURGk",
"version": 1
}
}

Some files were not shown because too many files have changed in this diff Show More