Warn on PCIe link speed degradation and collect lspci -vvv in techdump
- collector/pcie: add applyPCIeLinkSpeedWarning that sets status=Warning and ErrorDescription when current link speed is below maximum negotiated speed (e.g. Gen1 running on a Gen5 slot) - collector/pcie: add pcieLinkSpeedRank helper for Gen string comparison - collector/pcie_filter_test: cover degraded and healthy link speed cases - platform/techdump: collect lspci -vvv → lspci-vvv.txt for LnkCap/LnkSta Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -2,6 +2,7 @@ package collector
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bee/audit/internal/schema"
|
"bee/audit/internal/schema"
|
||||||
|
"fmt"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
"os/exec"
|
"os/exec"
|
||||||
"strconv"
|
"strconv"
|
||||||
@@ -172,6 +173,9 @@ func parseLspciDevice(fields map[string]string) schema.HardwarePCIeDevice {
|
|||||||
|
|
||||||
// SVendor/SDevice available but not in schema — skip
|
// SVendor/SDevice available but not in schema — skip
|
||||||
|
|
||||||
|
// Warn if PCIe link is running below its maximum negotiated speed.
|
||||||
|
applyPCIeLinkSpeedWarning(&dev)
|
||||||
|
|
||||||
return dev
|
return dev
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -241,6 +245,41 @@ func readPCIStringAttribute(bdf, attribute string) (string, bool) {
|
|||||||
return value, true
|
return value, true
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// applyPCIeLinkSpeedWarning sets the device status to Warning if the current PCIe link
|
||||||
|
// speed is below the maximum negotiated speed supported by both ends.
|
||||||
|
func applyPCIeLinkSpeedWarning(dev *schema.HardwarePCIeDevice) {
|
||||||
|
if dev.LinkSpeed == nil || dev.MaxLinkSpeed == nil {
|
||||||
|
return
|
||||||
|
}
|
||||||
|
if pcieLinkSpeedRank(*dev.LinkSpeed) < pcieLinkSpeedRank(*dev.MaxLinkSpeed) {
|
||||||
|
warn := statusWarning
|
||||||
|
dev.Status = &warn
|
||||||
|
desc := fmt.Sprintf("PCIe link speed degraded: running at %s, capable of %s", *dev.LinkSpeed, *dev.MaxLinkSpeed)
|
||||||
|
dev.ErrorDescription = &desc
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// pcieLinkSpeedRank returns a numeric rank for a normalized Gen string (e.g. "Gen4" → 4).
|
||||||
|
// Returns 0 for unrecognised values so comparisons fail safe.
|
||||||
|
func pcieLinkSpeedRank(gen string) int {
|
||||||
|
switch gen {
|
||||||
|
case "Gen1":
|
||||||
|
return 1
|
||||||
|
case "Gen2":
|
||||||
|
return 2
|
||||||
|
case "Gen3":
|
||||||
|
return 3
|
||||||
|
case "Gen4":
|
||||||
|
return 4
|
||||||
|
case "Gen5":
|
||||||
|
return 5
|
||||||
|
case "Gen6":
|
||||||
|
return 6
|
||||||
|
default:
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
func normalizePCILinkSpeed(raw string) string {
|
func normalizePCILinkSpeed(raw string) string {
|
||||||
raw = strings.TrimSpace(strings.ToLower(raw))
|
raw = strings.TrimSpace(strings.ToLower(raw))
|
||||||
switch {
|
switch {
|
||||||
|
|||||||
@@ -1,6 +1,7 @@
|
|||||||
package collector
|
package collector
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"bee/audit/internal/schema"
|
||||||
"encoding/json"
|
"encoding/json"
|
||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
@@ -141,3 +142,77 @@ func TestNormalizePCILinkSpeed(t *testing.T) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestApplyPCIeLinkSpeedWarning(t *testing.T) {
|
||||||
|
ptr := func(s string) *string { return &s }
|
||||||
|
|
||||||
|
tests := []struct {
|
||||||
|
name string
|
||||||
|
linkSpeed *string
|
||||||
|
maxSpeed *string
|
||||||
|
wantWarning bool
|
||||||
|
wantGenIn string // substring expected in ErrorDescription when warning
|
||||||
|
}{
|
||||||
|
{
|
||||||
|
name: "degraded Gen1 vs Gen5",
|
||||||
|
linkSpeed: ptr("Gen1"),
|
||||||
|
maxSpeed: ptr("Gen5"),
|
||||||
|
wantWarning: true,
|
||||||
|
wantGenIn: "Gen1",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "at max Gen5",
|
||||||
|
linkSpeed: ptr("Gen5"),
|
||||||
|
maxSpeed: ptr("Gen5"),
|
||||||
|
wantWarning: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "degraded Gen4 vs Gen5",
|
||||||
|
linkSpeed: ptr("Gen4"),
|
||||||
|
maxSpeed: ptr("Gen5"),
|
||||||
|
wantWarning: true,
|
||||||
|
wantGenIn: "Gen4",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "missing current speed — no warning",
|
||||||
|
linkSpeed: nil,
|
||||||
|
maxSpeed: ptr("Gen5"),
|
||||||
|
wantWarning: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "missing max speed — no warning",
|
||||||
|
linkSpeed: ptr("Gen1"),
|
||||||
|
maxSpeed: nil,
|
||||||
|
wantWarning: false,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, tt := range tests {
|
||||||
|
t.Run(tt.name, func(t *testing.T) {
|
||||||
|
dev := schema.HardwarePCIeDevice{}
|
||||||
|
ok := statusOK
|
||||||
|
dev.Status = &ok
|
||||||
|
dev.LinkSpeed = tt.linkSpeed
|
||||||
|
dev.MaxLinkSpeed = tt.maxSpeed
|
||||||
|
|
||||||
|
applyPCIeLinkSpeedWarning(&dev)
|
||||||
|
|
||||||
|
gotWarn := dev.Status != nil && *dev.Status == statusWarning
|
||||||
|
if gotWarn != tt.wantWarning {
|
||||||
|
t.Fatalf("wantWarning=%v gotWarning=%v (status=%v)", tt.wantWarning, gotWarn, dev.Status)
|
||||||
|
}
|
||||||
|
if tt.wantWarning {
|
||||||
|
if dev.ErrorDescription == nil {
|
||||||
|
t.Fatal("expected ErrorDescription to be set")
|
||||||
|
}
|
||||||
|
if !strings.Contains(*dev.ErrorDescription, tt.wantGenIn) {
|
||||||
|
t.Fatalf("ErrorDescription %q does not contain %q", *dev.ErrorDescription, tt.wantGenIn)
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
if dev.ErrorDescription != nil {
|
||||||
|
t.Fatalf("unexpected ErrorDescription: %s", *dev.ErrorDescription)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
@@ -20,6 +20,7 @@ var techDumpFixedCommands = []struct {
|
|||||||
{Name: "dmidecode", Args: []string{"-t", "4"}, File: "dmidecode-type4.txt"},
|
{Name: "dmidecode", Args: []string{"-t", "4"}, File: "dmidecode-type4.txt"},
|
||||||
{Name: "dmidecode", Args: []string{"-t", "17"}, File: "dmidecode-type17.txt"},
|
{Name: "dmidecode", Args: []string{"-t", "17"}, File: "dmidecode-type17.txt"},
|
||||||
{Name: "lspci", Args: []string{"-vmm", "-D"}, File: "lspci-vmm.txt"},
|
{Name: "lspci", Args: []string{"-vmm", "-D"}, File: "lspci-vmm.txt"},
|
||||||
|
{Name: "lspci", Args: []string{"-vvv"}, File: "lspci-vvv.txt"},
|
||||||
{Name: "lsblk", Args: []string{"-J", "-d", "-o", "NAME,TYPE,SIZE,SERIAL,MODEL,TRAN,HCTL"}, File: "lsblk.json"},
|
{Name: "lsblk", Args: []string{"-J", "-d", "-o", "NAME,TYPE,SIZE,SERIAL,MODEL,TRAN,HCTL"}, File: "lsblk.json"},
|
||||||
{Name: "sensors", Args: []string{"-j"}, File: "sensors.json"},
|
{Name: "sensors", Args: []string{"-j"}, File: "sensors.json"},
|
||||||
{Name: "ipmitool", Args: []string{"fru", "print"}, File: "ipmitool-fru.txt"},
|
{Name: "ipmitool", Args: []string{"fru", "print"}, File: "ipmitool-fru.txt"},
|
||||||
|
|||||||
Reference in New Issue
Block a user