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

Jump to bottom

Add examples for three existing failure policy actions. #601

Merged
merged 9 commits into from
Sep 20, 2024
Merged

Add examples for three existing failure policy actions. #601

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
fd29fa0
Add examples for three existing failure policy actions.
Jun 10, 2024
f19acf0
Add example for configurable failure policy using a rule with onJobFa…
Jun 13, 2024
13bc476
Correct the name of the jobset in 'examples/failure-policy/onjobfailu…
Jun 13, 2024
dad8964
Add example using onJobFailureReasons with the selected reason being …
Jun 14, 2024
aa983cc
Merge branch 'kubernetes-sigs:main' into adding-configurable-failure-…
Sep 4, 2024
c740191
Add example similar to a host maintenance event.
Sep 4, 2024
4be32d6
Add short descriptions of expected behavior in examples.
Sep 4, 2024
1736c95
Fix grammatical error.
Sep 11, 2024
d097262
Add commment describing host maintenance example.
Sep 11, 2024
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
60 changes: 60 additions & 0 deletions examples/failure-policy/failjobset-action.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
apiVersion: jobset.x-k8s.io/v1alpha2
ahg-g marked this conversation as resolved.
Show resolved Hide resolved
kind: JobSet
metadata:
name: failjobset-action-example
spec:
failurePolicy:
danielvegamyhre marked this conversation as resolved.
Show resolved Hide resolved
maxRestarts: 3
rules:
- action: FailJobSet
targetReplicatedJobs:
- leader
replicatedJobs:
- name: leader
replicas: 1
template:
spec:
# Set backoff limit to 0 so job will immediately fail if any pod fails.
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: leader
image: bash:latest
command:
- bash
- -xc
- |
echo "JOB_COMPLETION_INDEX=$JOB_COMPLETION_INDEX"
if [[ "$JOB_COMPLETION_INDEX" == "0" ]]; then
for i in $(seq 10 -1 1)
do
echo "Sleeping in $i"
sleep 1
done
exit 1
fi
for i in $(seq 1 1000)
do
echo "$i"
sleep 1
done
- name: workers
replicas: 1
template:
spec:
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: worker
image: bash:latest
command:
- bash
- -xc
- |
sleep 1000
71 changes: 71 additions & 0 deletions examples/failure-policy/onjobfailurereasons-present-podfailurepolicy.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
apiVersion: jobset.x-k8s.io/v1alpha2
kind: JobSet
metadata:
name: onjobfailurereasons-podfailurepolicy-example
spec:
failurePolicy:
maxRestarts: 3
rules:
- action: RestartJobSetAndIgnoreMaxRestarts
targetReplicatedJobs:
- leader
onJobFailureReasons:
- PodFailurePolicy
replicatedJobs:
- name: leader
replicas: 1
template:
spec:
# Set backoff limit to 0 so job will immediately fail if any pod fails.
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
restartPolicy: Never
containers:
- name: leader
image: bash:latest
command:
- bash
- -xc
- |
echo "JOB_COMPLETION_INDEX=$JOB_COMPLETION_INDEX"
if [[ "$JOB_COMPLETION_INDEX" == "0" ]]; then
for i in $(seq 10 -1 1)
do
echo "Sleeping in $i"
sleep 1
done
exit 1
fi
for i in $(seq 1 1000)
do
echo "$i"
sleep 1
done
podFailurePolicy:
rules:
- action: FailJob
onPodConditions: []
onExitCodes:
containerName: leader
operator: In
values: [1]
- name: workers
replicas: 1
template:
spec:
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: worker
image: bash:latest
command:
- bash
- -xc
- |
sleep 1000
62 changes: 62 additions & 0 deletions examples/failure-policy/onjobfailurereasons-present.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
apiVersion: jobset.x-k8s.io/v1alpha2
kind: JobSet
metadata:
name: onjobfailurereasons-present-example
spec:
failurePolicy:
maxRestarts: 3
rules:
- action: RestartJobSetAndIgnoreMaxRestarts
targetReplicatedJobs:
- leader
onJobFailureReasons:
- BackoffLimitExceeded
replicatedJobs:
- name: leader
replicas: 1
template:
spec:
# Set backoff limit to 0 so job will immediately fail if any pod fails.
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: leader
image: bash:latest
command:
- bash
- -xc
- |
echo "JOB_COMPLETION_INDEX=$JOB_COMPLETION_INDEX"
if [[ "$JOB_COMPLETION_INDEX" == "0" ]]; then
for i in $(seq 10 -1 1)
do
echo "Sleeping in $i"
sleep 1
done
exit 1
fi
for i in $(seq 1 1000)
do
echo "$i"
sleep 1
done
- name: workers
replicas: 1
template:
spec:
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: worker
image: bash:latest
command:
- bash
- -xc
- |
sleep 1000
60 changes: 60 additions & 0 deletions examples/failure-policy/restartjobset-action.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
apiVersion: jobset.x-k8s.io/v1alpha2
kind: JobSet
metadata:
name: restartjobset-action-example
spec:
failurePolicy:
maxRestarts: 3
rules:
- action: RestartJobSet
targetReplicatedJobs:
- leader
replicatedJobs:
- name: leader
replicas: 1
template:
spec:
# Set backoff limit to 0 so job will immediately fail if any pod fails.
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: leader
image: bash:latest
command:
- bash
- -xc
- |
echo "JOB_COMPLETION_INDEX=$JOB_COMPLETION_INDEX"
if [[ "$JOB_COMPLETION_INDEX" == "0" ]]; then
for i in $(seq 10 -1 1)
do
echo "Sleeping in $i"
sleep 1
done
exit 1
fi
for i in $(seq 1 1000)
do
echo "$i"
sleep 1
done
- name: workers
replicas: 1
template:
spec:
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: worker
image: bash:latest
command:
- bash
- -xc
- |
sleep 1000
61 changes: 61 additions & 0 deletions examples/failure-policy/restartjobsetandignoremaxrestarts-action.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
apiVersion: jobset.x-k8s.io/v1alpha2
kind: JobSet
metadata:
# rjimr stands for "restartjobsetandignoremaxrestarts"
name: rjimr-action-example
spec:
failurePolicy:
maxRestarts: 3
rules:
danielvegamyhre marked this conversation as resolved.
Show resolved Hide resolved
- action: RestartJobSetAndIgnoreMaxRestarts
targetReplicatedJobs:
- leader
replicatedJobs:
- name: leader
replicas: 1
template:
spec:
# Set backoff limit to 0 so job will immediately fail if any pod fails.
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: leader
image: bash:latest
command:
- bash
- -xc
- |
echo "JOB_COMPLETION_INDEX=$JOB_COMPLETION_INDEX"
if [[ "$JOB_COMPLETION_INDEX" == "0" ]]; then
for i in $(seq 10 -1 1)
do
echo "Sleeping in $i"
sleep 1
done
exit 1
fi
for i in $(seq 1 1000)
do
echo "$i"
sleep 1
done
- name: workers
replicas: 1
template:
spec:
backoffLimit: 0
completions: 2
parallelism: 2
template:
spec:
containers:
- name: worker
image: bash:latest
command:
- bash
- -xc
- |
sleep 1000