Skip to content

fix(monitor): clamp DeviceNum to maxDevices to prevent scrape-path panic #2400

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
hami-robot merged 1 commit into from
Aug 6, 2026
+22 −2
Merged

fix(monitor): clamp DeviceNum to maxDevices to prevent scrape-path panic #2400

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
2 changes: 1 addition & 1 deletion pkg/monitor/nvidia/v0/spec.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ func (s Spec) DeviceMax() int {
}

func (s Spec) DeviceNum() int {
return int(s.sr.num)
return int(min(s.sr.num, uint64(maxDevices)))
}

// activeProcs returns the process slots currently in use. procnum is read from
Expand Down
2 changes: 2 additions & 0 deletions pkg/monitor/nvidia/v0/spec_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,8 @@ func TestSpec_DeviceNum(t *testing.T) {
tests := []specTest{
{name: "device num is 4", spec: &Spec{sr: &sharedRegionT{num: 4}}, expected: 4},
{name: "device num is 8", spec: &Spec{sr: &sharedRegionT{num: 8}}, expected: 8},
{name: "num larger than maxDevices is clamped", spec: &Spec{sr: &sharedRegionT{num: 9999}}, expected: maxDevices},
{name: "high-bit uint64 num is clamped not negative", spec: &Spec{sr: &sharedRegionT{num: 0x8000000000000001}}, expected: maxDevices},
}

for _, tt := range tests {
Expand Down
2 changes: 1 addition & 1 deletion pkg/monitor/nvidia/v1/spec.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ func (s Spec) DeviceMax() int {
}

func (s Spec) DeviceNum() int {
return int(s.sr.num)
return int(min(s.sr.num, uint64(maxDevices)))
}

// activeProcs returns the process slots currently in use. procnum is read from
Expand Down
18 changes: 18 additions & 0 deletions pkg/monitor/nvidia/v1/spec_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,24 @@ func Test_DeviceNum(t *testing.T) {
},
want: int(4),
},
{
name: "num larger than maxDevices is clamped",
args: &Spec{
sr: &sharedRegionT{
num: 9999,
},
},
want: maxDevices,
},
{
name: "high-bit uint64 num is clamped not negative",
args: &Spec{
sr: &sharedRegionT{
num: 0x8000000000000001,
},
},
want: maxDevices,
},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
Expand Down
Loading