Skip to content

Cleanup: mark deprecating for inconstant metric label #1294

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Cleanup: mark deprecating for inconstant metric label #1294

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
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 @@ -75,7 +75,7 @@ func (cc ClusterManagerCollector) Collect(ch chan<- prometheus.Metric) {
)
nodevGPUMemoryAllocatedDesc := prometheus.NewDesc(
"GPUDeviceMemoryAllocated",
"Device memory allocated for a certain GPU",
"Device memory allocated for a certain GPU. The label devicecores will be deprecated in 2.8.0",
[]string{"nodeid", "deviceuuid", "deviceidx", "devicecores"}, nil,
)
nodevGPUSharedNumDesc := prometheus.NewDesc(
Expand All @@ -91,7 +91,7 @@ func (cc ClusterManagerCollector) Collect(ch chan<- prometheus.Metric) {
)
nodeGPUOverview := prometheus.NewDesc(
"nodeGPUOverview",
"GPU overview on a certain node",
"GPU overview on a certain node. The label devicecores will be deprecated in 2.8.0",
[]string{"nodeid", "deviceuuid", "deviceidx", "devicecores", "sharedcontainers", "devicememorylimit", "devicetype"}, nil,
)
nodeGPUMemoryPercentage := prometheus.NewDesc(
Expand Down
11 changes: 3 additions & 8 deletions cmd/vGPUmonitor/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,8 +105,8 @@ var (
)
ctrDeviceMemorydesc = prometheus.NewDesc(
"Device_memory_desc_of_container",
"Container device meory description",
[]string{"podnamespace", "podname", "ctrname", "vdeviceid", "deviceuuid", "context", "module", "data", "offset"}, nil,
"Container device memory description.",
[]string{"podnamespace", "podname", "ctrname", "vdeviceid", "deviceuuid"}, nil,
)
ctrDeviceUtilizationdesc = prometheus.NewDesc(
"Device_utilization_desc_of_container",
Expand Down Expand Up @@ -378,10 +378,6 @@ func (cc ClusterManagerCollector) collectContainerMetrics(ch chan<- prometheus.M
// Collect device metrics
memoryTotal := c.Info.DeviceMemoryTotal(i)
memoryLimit := c.Info.DeviceMemoryLimit(i)
memoryContextSize := c.Info.DeviceMemoryContextSize(i)
memoryModuleSize := c.Info.DeviceMemoryModuleSize(i)
memoryBufferSize := c.Info.DeviceMemoryBufferSize(i)
memoryOffset := c.Info.DeviceMemoryOffset(i)
smUtil := c.Info.DeviceSmUtil(i)
lastKernelTime := c.Info.LastKernelTime()

Expand All @@ -399,8 +395,7 @@ func (cc ClusterManagerCollector) collectContainerMetrics(ch chan<- prometheus.M
}

// Send memory-related metrics with additional labels
memoryLabels := append(labels, fmt.Sprint(memoryContextSize), fmt.Sprint(memoryModuleSize), fmt.Sprint(memoryBufferSize), fmt.Sprint(memoryOffset))
if err := sendMetric(ch, ctrDeviceMemorydesc, prometheus.CounterValue, float64(memoryTotal), memoryLabels...); err != nil {
if err := sendMetric(ch, ctrDeviceMemorydesc, prometheus.GaugeValue, float64(memoryTotal)); err != nil {
klog.Errorf("Failed to send memory-related metrics for device %d in Pod %s/%s, Container %s: %v", i, pod.Namespace, pod.Name, ctr.Name, err)
return err
}
Expand Down
Loading