Skip to content

Commit 9ac3758

Browse files
authored
fix: add missing recommended actions as per xid analyzer catalog (#1343)
1 parent 55ce76d commit 9ac3758

2 files changed

Lines changed: 19 additions & 2 deletions

File tree

health-monitors/syslog-health-monitor/pkg/common/common.go

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,8 +79,17 @@ func MapActionStringToProto(s string) pb.RecommendedAction {
7979
// XID_154_EVAL is considered equivalent to RESTART_APP.
8080
case "RESTART_APP", "IGNORE", "XID_154_EVAL":
8181
return pb.RecommendedAction_NONE
82-
case "WORKFLOW_XID_48", "RESET_GPU", "RESET_FABRIC":
82+
// RECOVER_FEATURE_RESET_GPU: power-smoothing feature recovery (XID 163);
83+
// trigger guidance is "reload the driver or reset the GPU" — same proto
84+
// target as the RESET_GPU bucket.
85+
case "WORKFLOW_XID_48", "RESET_GPU", "RECOVER_FEATURE_RESET_GPU":
8386
return pb.RecommendedAction_COMPONENT_RESET
87+
// WORKFLOW_XID_168: WPR/ECC config issue (XID 168). Catalog guidance is
88+
// "either ECC should be enabled (to enable row-remapping) or boot
89+
// re-attempted with shifted WPR" — reboot the VM so init can re-attempt
90+
// with a shifted Write-Protect-Region.
91+
case "WORKFLOW_XID_168", "RESET_FABRIC":
92+
return pb.RecommendedAction_RESTART_VM
8493
default:
8594
slog.Warn("Unknown action string, defaulting to CONTACT_SUPPORT", "action", s)
8695
return pb.RecommendedAction_CONTACT_SUPPORT

health-monitors/syslog-health-monitor/pkg/common/common_test.go

Lines changed: 9 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -102,9 +102,17 @@ func TestMapActionStringToProto(t *testing.T) {
102102
expectedOutput: pb.RecommendedAction_COMPONENT_RESET,
103103
},
104104
{
105-
input: "RESET_FABRIC",
105+
input: "RECOVER_FEATURE_RESET_GPU",
106106
expectedOutput: pb.RecommendedAction_COMPONENT_RESET,
107107
},
108+
{
109+
input: "WORKFLOW_XID_168",
110+
expectedOutput: pb.RecommendedAction_RESTART_VM,
111+
},
112+
{
113+
input: "RESET_FABRIC",
114+
expectedOutput: pb.RecommendedAction_RESTART_VM,
115+
},
108116
{
109117
input: "NONE",
110118
expectedOutput: pb.RecommendedAction_NONE,

0 commit comments

Comments
 (0)