Skip to content

feat: mark persistence mode diable as warning level #225

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
ambermingxin merged 1 commit into from
Jun 25, 2026
Merged

feat: mark persistence mode diable as warning level #225

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
6 changes: 5 additions & 1 deletion ..._party/fleet-intelligence-sdk/components/accelerator/nvidia/persistence-mode/component.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,6 +170,7 @@ func (c *component) Check() components.CheckResult {
persistenceMode, err := c.getPersistenceModeFunc(uuid, dev)
if err != nil {
cr.err = err
// deliberately stayed Unhealthy to indicate NVML query errors, GPU-lost, and GPU-requires-reset
cr.health = apiv1.HealthStateTypeUnhealthy
cr.reason = "error getting persistence mode"

Expand Down Expand Up @@ -208,7 +209,10 @@ func (c *component) Check() components.CheckResult {
}

if len(notEnabled) > 0 {
cr.health = apiv1.HealthStateTypeUnhealthy
// Persistence mode being disabled is a configuration issue that does not
// affect running workloads, so it is flagged as a warning (Degraded)
// rather than critical (Unhealthy).
cr.health = apiv1.HealthStateTypeDegraded
if len(notEnabled) == len(cr.PersistenceModes) {
cr.reason = fmt.Sprintf("all %d GPU(s) disabled persistence mode", len(devs))
} else {
Expand Down
8 changes: 4 additions & 4 deletions ...y/fleet-intelligence-sdk/components/accelerator/nvidia/persistence-mode/component_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -337,8 +337,8 @@ func TestCheck_MultipleDevices(t *testing.T) {
require.True(t, ok, "result should be of type *checkResult")

require.NotNil(t, data, "data should not be nil")
// This should be unhealthy since one device has persistence mode supported but not enabled
assert.Equal(t, apiv1.HealthStateTypeUnhealthy, data.health, "data should be marked unhealthy")
// This should be degraded (warning) since one device has persistence mode supported but not enabled
assert.Equal(t, apiv1.HealthStateTypeDegraded, data.health, "data should be marked degraded")
assert.Equal(t, "gpu-uuid-456 persistence mode supported but not enabled", data.reason)
assert.Len(t, data.PersistenceModes, 2)

Expand Down Expand Up @@ -734,7 +734,7 @@ func TestPersistenceModeCheck(t *testing.T) {
{UUID: "GPU-1", Supported: true, Enabled: true},
{UUID: "GPU-2", Supported: true, Enabled: false},
},
expectedHealth: apiv1.HealthStateTypeUnhealthy,
expectedHealth: apiv1.HealthStateTypeDegraded,
expectedReasonCmp: "GPU-2 persistence mode supported but not enabled",
},
{
Expand All @@ -743,7 +743,7 @@ func TestPersistenceModeCheck(t *testing.T) {
{UUID: "GPU-1", Supported: true, Enabled: false},
{UUID: "GPU-2", Supported: true, Enabled: false},
},
expectedHealth: apiv1.HealthStateTypeUnhealthy,
expectedHealth: apiv1.HealthStateTypeDegraded,
expectedReasonCmp: "all 2 GPU(s) disabled persistence mode",
},
{
Expand Down
Loading