Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix tests in sig-node related to CRIv1 update #28071

Merged
merged 4 commits into from
Dec 6, 2022
Merged

fix tests in sig-node related to CRIv1 update #28071

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4cbbb58
fix node-kubelet-containerd-resource-managers job
akhilerm Nov 21, 2022
5e855d6
update image-config-serial images
akhilerm Nov 21, 2022
ff69de5
use separate containerd config file for systemd cgroup driver
akhilerm Nov 29, 2022
5f6e009
remove quoting TOML boolean
akhilerm Dec 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions config/jobs/kubernetes/sig-node/containerd.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,7 +535,7 @@ periodics:
- --deployment=node
- --gcp-zone=us-west1-b
- --node-args=--image-config-file=/workspace/test-infra/jobs/e2e_node/containerd/image-config-serial.yaml
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --node-tests=true
- --provider=gce
- --test_args=--nodes=1 --focus="\[NodeFeature:Eviction\]"
Expand Down Expand Up @@ -1171,7 +1171,7 @@ periodics:
- --gcp-project-type=node-e2e-project
- --gcp-zone=us-west1-b
- --node-args=--image-config-file=/workspace/test-infra/jobs/e2e_node/containerd/image-config-serial-resource-managers.yaml
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --node-tests=true
- --provider=gce
- --test_args=--nodes=1 --focus="\[Feature:CPUManager\]|\[Feature:MemoryManager\]|\[Feature:TopologyManager\]"
Expand Down
2 changes: 1 addition & 1 deletion config/jobs/kubernetes/sig-node/node-kubelet.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ periodics:
- --deployment=node
- --gcp-zone=us-west1-b
- --node-args=--image-config-file=/workspace/test-infra/jobs/e2e_node/containerd/image-config-serial.yaml
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --node-tests=true
- --provider=gce
- --test_args=--nodes=1 --timeout=4h --focus="\[Serial\]" --skip="\[Flaky\]|\[Benchmark\]|\[NodeSpecialFeature:.+\]|\[NodeSpecialFeature\]|\[NodeAlphaFeature:.+\]|\[NodeAlphaFeature\]|\[NodeFeature:Eviction\]"
Expand Down
6 changes: 3 additions & 3 deletions config/jobs/kubernetes/sig-node/sig-node-presubmit.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -388,7 +388,7 @@ presubmits:
- --deployment=node
- --gcp-zone=us-west1-b
- --node-args=--image-config-file=/workspace/test-infra/jobs/e2e_node/containerd/image-config-serial.yaml
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--node-test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --node-tests=true
- --provider=gce
- --test_args=--nodes=1 --timeout=4h --focus="\[Serial\]" --skip="\[Flaky\]|\[Benchmark\]|\[NodeSpecialFeature:.+\]|\[NodeSpecialFeature\]|\[NodeAlphaFeature:.+\]|\[NodeAlphaFeature\]|\[NodeFeature:Eviction\]"
Expand Down Expand Up @@ -454,7 +454,7 @@ presubmits:
- --parallelism=1
- --focus-regex=\[Serial\]
- --skip-regex=\[Flaky\]|\[Benchmark\]|\[NodeSpecialFeature:.+\]|\[NodeSpecialFeature\]|\[NodeAlphaFeature:.+\]|\[NodeAlphaFeature\]|\[NodeFeature:Eviction\]
- '--test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--test-args=--feature-gates=LocalStorageCapacityIsolation=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --image-config-file=/home/prow/go/src/k8s.io/test-infra/jobs/e2e_node/containerd/image-config-serial.yaml
- name: pull-kubernetes-node-kubelet-serial-cpu-manager
cluster: k8s-infra-prow-build
Expand Down Expand Up @@ -1678,7 +1678,7 @@ presubmits:
- --deployment=node
- --gcp-zone=us-west1-b
- --node-args=--image-config-file=/workspace/test-infra/jobs/e2e_node/containerd/image-config-serial.yaml
- '--node-test-args=--feature-gates=PodDisruptionConditions=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- '--node-test-args=--feature-gates=PodDisruptionConditions=true --container-runtime-endpoint=unix:///run/containerd/containerd.sock --container-runtime-process-name=/usr/bin/containerd --container-runtime-pid-file= --kubelet-flags="--cgroup-driver=systemd --cgroups-per-qos=true --cgroup-root=/ --runtime-cgroups=/system.slice/containerd.service" --extra-log="{\"name\": \"containerd.log\", \"journalctl\": [\"-u\", \"containerd*\"]}"'
- --node-tests=true
- --provider=gce
- --test_args=--nodes=1 --timeout=180m --skip="" --focus="\[NodeFeature:PodDisruptionConditions\]"
Expand Down
40 changes: 40 additions & 0 deletions jobs/e2e_node/containerd/config-systemd.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
# This file is a copy of config.toml with SystemdCgroup enabled
#
# TODO:@akhilerm Once all the tests move to use cgroupv2, this file wont be needed.
# This should merge with config.toml and it should be used everywhere
version = 2
required_plugins = ["io.containerd.grpc.v1.cri"]
# Kubernetes doesn't use containerd restart manager.
disabled_plugins = ["io.containerd.internal.v1.restart"]
oom_score = -999

[debug]
level = "debug"

[plugins."io.containerd.grpc.v1.cri"]
stream_server_address = "127.0.0.1"
max_container_log_line_size = 262144
[plugins."io.containerd.grpc.v1.cri".cni]
bin_dir = "/home/containerd/"
conf_dir = "/etc/cni/net.d"
conf_template = "/home/containerd/cni.template"
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
endpoint = ["https://mirror.gcr.io","https://registry-1.docker.io"]

[plugins."io.containerd.grpc.v1.cri".containerd]
default_runtime_name = "runc"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
SystemdCgroup = true

# Runtime handler used for runtime class test.
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.test-handler]
runtime_type = "io.containerd.runc.v2"

# Enable registry.k8s.io as the primary mirror for k8s.gcr.io
# See: https://github.com/kubernetes/k8s.io/issues/3411
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."k8s.gcr.io"]
endpoint = ["https://registry.k8s.io", "https://k8s.gcr.io",]

Comment on lines +35 to +39
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Now registry.k8s.io is GA (and introduced in the master branch of k/k) there is no specific value to do this.
we should remove this as a follow-up.

Copy link
Member Author

@akhilerm akhilerm Nov 30, 2022 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will create a separate cleanup PR for that, so that the original config.toml can also be fixed.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ameukam Found this comment in the referring issue for the migration, So should we wait for some more time before switching?


10 changes: 5 additions & 5 deletions jobs/e2e_node/containerd/image-config-serial-resource-managers.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,14 +3,14 @@
# `gcloud compute --project <to-project> images create <image-name> --source-disk=<image-name>`
images:
ubuntu:
image_family: pipeline-1-24
project: ubuntu-os-gke-cloud
image_family: ubuntu-2204-lts
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Out of curiosity, why stop use the GKE images ?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ameukam So that it will pick up the latest public ubuntu 22.04 image which is cgroupv2 enabled. Ref

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok. I had a wrong assumption of pipeline-1-24. I thought since this family is ubuntu-based:

$gcloud compute images describe-from-family pipeline-1-24 --project ubuntu-os-gke-cloud --format='value(name,selfLink)'  
ubuntu-gke-2204-1-24-v20221128	https://www.googleapis.com/compute/v1/projects/ubuntu-os-gke-cloud/global/images/ubuntu-gke-2204-1-24-v20221128

the node(s) will have cgroupsv2 enabled.

project: ubuntu-os-cloud
# Using `n1-standard-4` to enable CPU manager node e2e tests.
machine: n1-standard-4
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config.toml"
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config-systemd.toml"
cos-stable1:
image_family: cos-89-lts # deprecated after March 2023 (https://cloud.google.com/container-optimized-os/docs/release-notes)
image_family: cos-stable
project: cos-cloud
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config.toml"
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config-systemd.toml"
# Using `n1-standard-4` to enable CPU manager node e2e tests.
machine: n1-standard-4
14 changes: 7 additions & 7 deletions jobs/e2e_node/containerd/image-config-serial.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,20 @@
images:
ubuntu:
image_family: pipeline-1-24
project: ubuntu-os-gke-cloud
image_family: ubuntu-2204-lts
project: ubuntu-os-cloud
machine: n1-standard-2 # These tests need a lot of memory
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config.toml"
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config-systemd.toml"
cos-stable2:
image_family: cos-93-lts # deprecated after October 2023 (https://cloud.google.com/container-optimized-os/docs/release-notes)
image_family: cos-stable
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@SergeyKanzhelev Why were we maintaining 2 separate cos versions for the tests in image-config-serial ?

project: cos-cloud
machine: n1-standard-2 # These tests need a lot of memory
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config.toml"
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config-systemd.toml"
resources:
accelerators:
- type: nvidia-tesla-k80
count: 2
cos-stable1:
image_family: cos-89-lts # deprecated after March 2023 (https://cloud.google.com/container-optimized-os/docs/release-notes)
image_family: cos-stable
project: cos-cloud
machine: n1-standard-2 # These tests need a lot of memory
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config.toml"
metadata: "user-data</workspace/test-infra/jobs/e2e_node/containerd/init.yaml,cni-template</workspace/test-infra/jobs/e2e_node/containerd/cni.template,containerd-config</workspace/test-infra/jobs/e2e_node/containerd/config-systemd.toml"