Skip to content

[CP 1202] GPUOP-583 584 ANR fixes #475

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

Merged
sajmera-pensando merged 1 commit into from
Mar 18, 2026
Merged

[CP 1202] GPUOP-583 584 ANR fixes #475

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 21 additions & 2 deletions internal/controllers/remediation/scripts/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,26 @@
set -e
NODE_NAME='{{inputs.parameters.node_name}}'
JOB_NAME="{{workflow.name}}-test-run"
CM_NAME='{{workflow.name}}-test-configmap'

# Generate a unique job name under 63 characters
# Format: <truncated-workflow-name>-<short-uid>-test
WORKFLOW_NAME='{{workflow.name}}'
WORKFLOW_UID='{{workflow.uid}}'

# Extract last 8 characters of workflow UID for uniqueness
SHORT_UID="${WORKFLOW_UID: -8}"

# Calculate max length for workflow name prefix (63 - 8 (uid) - 1 (dash) - 5 ("-test") - 1 (dash) = 48)
MAX_PREFIX_LEN=48

# Truncate workflow name if needed
if [ ${#WORKFLOW_NAME} -gt $MAX_PREFIX_LEN ]; then
WORKFLOW_PREFIX="${WORKFLOW_NAME:0:$MAX_PREFIX_LEN}"
else
WORKFLOW_PREFIX="$WORKFLOW_NAME"
fi

JOB_NAME="${WORKFLOW_PREFIX}-${SHORT_UID}-test"
CM_NAME="${WORKFLOW_PREFIX}-${SHORT_UID}-cm"
FRAMEWORK='{{inputs.parameters.framework}}'
RECIPE='{{inputs.parameters.recipe}}'
ITERATIONS='{{inputs.parameters.iterations}}'
Expand Down
4 changes: 2 additions & 2 deletions internal/controllers/remediation_handler.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,7 +643,7 @@ func (h *remediationMgrHelper) createDefaultWorkflowTemplate(ctx context.Context
Name: "inbuilt",
Metadata: instanceIDMeta,
Steps: []workflowv1alpha1.ParallelSteps{
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "autostart", Template: "suspend", When: "{{workflow.parameters.auto_start}} == 'false'"}}}, // If auto start is disabled, workflow will be created in suspended state and needs to be manually resumed by user
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "autostart", Template: "suspend", When: "{{workflow.parameters.auto_start}} == false"}}}, // If auto start is disabled, workflow will be created in suspended state and needs to be manually resumed by user
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "applylabels", Template: "applylabels"}}},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "taint", Template: "taint"}}},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "drain", Template: "drain"}}},
Expand All @@ -662,7 +662,7 @@ func (h *remediationMgrHelper) createDefaultWorkflowTemplate(ctx context.Context
},
},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "suspend", Template: "suspend"}}},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "reboot", Template: "reboot", ContinueOn: &workflowv1alpha1.ContinueOn{Failed: true}, When: "{{workflow.parameters.skipRebootStep}} == 'false'"}}},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "reboot", Template: "reboot", ContinueOn: &workflowv1alpha1.ContinueOn{Failed: true}, When: "{{workflow.parameters.skipRebootStep}} == false"}}},
{Steps: []workflowv1alpha1.WorkflowStep{{Name: "test", Template: "test", ContinueOn: &workflowv1alpha1.ContinueOn{Failed: true}}}},
{Steps: []workflowv1alpha1.WorkflowStep{
{
Expand Down
Loading