Skip to content

fix(metrics): add device_type label to node memory ratio metrics (#2370) #2554

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
archlitchi merged 2 commits into from
Aug 18, 2026
Merged

fix(metrics): add device_type label to node memory ratio metrics (#2370) #2554

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7fb437d
fix(metrics): add device_type label to node memory ratio metrics (#2370)
princexpoddar Aug 4, 2026
7a9cec2
revert(metrics): preserve legacy mode label contract for nodeGPUMemor…
princexpoddar Aug 11, 2026
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
4 changes: 2 additions & 2 deletions cmd/scheduler/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,7 @@ func (cc ClusterManagerCollector) collectNodeMetrics(ch chan<- prometheus.Metric
nodeGPUMemoryPercentage := prometheus.NewDesc(
"hami_node_gpu_memory_allocated_ratio",
"GPU Memory Allocated Percentage on a certain GPU",
[]string{"node", "device_uuid", "device_index"}, nil,
[]string{"node", "device_uuid", "device_index", "device_type"}, nil,
)
nodeGPUMigInstance := prometheus.NewDesc(
"hami_node_gpu_mig_instance_info",
Expand Down Expand Up @@ -261,7 +261,7 @@ func (cc ClusterManagerCollector) collectNodeMetrics(ch chan<- prometheus.Metric
}

if devs.Device.Totalmem > 0 {
if err := sendMetric(ch, nodeGPUMemoryPercentage, prometheus.GaugeValue, float64(devs.Device.Usedmem)/float64(devs.Device.Totalmem), nodeID, devs.Device.ID, fmt.Sprint(devs.Device.Index)); err != nil {
if err := sendMetric(ch, nodeGPUMemoryPercentage, prometheus.GaugeValue, float64(devs.Device.Usedmem)/float64(devs.Device.Totalmem), nodeID, devs.Device.ID, fmt.Sprint(devs.Device.Index), devs.Device.Type); err != nil {
klog.V(4).Infof("Failed to send nodeGPUMemoryPercentage metric: %v", err)
}
}
Expand Down
2 changes: 1 addition & 1 deletion cmd/scheduler/metrics_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -361,7 +361,7 @@ hami_gpu_core_limit_ratio{device_index="1",device_type="test-device",device_uuid
hami_gpu_core_limit_ratio{device_index="2",device_type="NVIDIA",device_uuid="normal-memory",node="node-1"} 2
# HELP hami_node_gpu_memory_allocated_ratio GPU Memory Allocated Percentage on a certain GPU
# TYPE hami_node_gpu_memory_allocated_ratio gauge
hami_node_gpu_memory_allocated_ratio{device_index="2",device_uuid="normal-memory",node="node-1"} 0.25
hami_node_gpu_memory_allocated_ratio{device_index="2",device_type="NVIDIA",device_uuid="normal-memory",node="node-1"} 0.25
# HELP nodeGPUMemoryPercentage GPU Memory Allocated Percentage on a certain GPU
# TYPE nodeGPUMemoryPercentage gauge
nodeGPUMemoryPercentage{deviceidx="2",deviceuuid="normal-memory",nodeid="node-1"} 0.25
Expand Down
Loading