Update metric names to fit metrics naming conventions

Signed-off-by: Shirly Radco <[email protected]>
zyjj1 · Aug 16, 2023 · dfdd479 · dfdd479
1 parent 5ee3885
commit dfdd479
Show file tree

Hide file tree

Showing 13 changed files with 159 additions and 168 deletions.
diff --git a/docs/metrics.md b/docs/metrics.md
@@ -12,7 +12,7 @@ All metrics documented here are auto-generated by the utility tool `tools/doc-ge
 ### kubevirt_info
 Version information.
 
-### kubevirt_allocatable_nodes_count
+### kubevirt_allocatable_nodes
 The number of nodes in the cluster that have the devices.kubevirt.io/kvm resource available. Type: Gauge.
 
 ### kubevirt_api_request_deprecated_total
@@ -21,9 +21,6 @@ The total number of requests to deprecated KubeVirt APIs. Type: Counter.
 ### kubevirt_configuration_emulation_enabled
 Indicates whether the Software Emulation is enabled in the configuration. Type: Gauge.
 
-### kubevirt_kvm_available_nodes_count
-The number of nodes in the cluster that have the devices.kubevirt.io/kvm resource available. Type: Gauge.
-
 ### kubevirt_migrate_vmi_data_processed_bytes
 The total Guest OS data processed and migrated to the new VM. Type: Gauge.
 
@@ -36,52 +33,46 @@ The rate of memory being dirty in the Guest OS. Type: Gauge.
 ### kubevirt_migrate_vmi_disk_transfer_rate_bytes
 The rate at which the disk is being transferred. Type: Gauge.
 
-### kubevirt_migrate_vmi_failed
-Number of failed migrations. Type: Gauge.
-
 ### kubevirt_migrate_vmi_memory_transfer_rate_bytes
 The rate at which the memory is being transferred. Type: Gauge.
 
-### kubevirt_migrate_vmi_pending_count
-Number of current pending migrations. Type: Gauge.
-
-### kubevirt_migrate_vmi_running_count
-Number of current running migrations. Type: Gauge.
-
-### kubevirt_migrate_vmi_scheduling_count
-Number of current scheduling migrations. Type: Gauge.
-
-### kubevirt_migrate_vmi_succeeded
-Number of migrations successfully executed. Type: Gauge.
+### kubevirt_nodes_with_kvm
+The number of nodes in the cluster that have the devices.kubevirt.io/kvm resource available. Type: Gauge.
 
 ### kubevirt_number_of_vms
 The number of VMs in the cluster by namespace. Type: Gauge.
 
-### kubevirt_virt_api_up_total
+### kubevirt_virt_api_up
 The number of virt-api pods that are up. Type: Gauge.
 
 ### kubevirt_virt_controller_leading
 Indication for an operating virt-controller. Type: Gauge.
 
 ### kubevirt_virt_controller_ready
-Indication for a virt-controller that is ready to take the lead. Type: Gauge.
-
-### kubevirt_virt_controller_ready_total
 The number of virt-controller pods that are ready. Type: Gauge.
 
-### kubevirt_virt_controller_up_total
+### kubevirt_virt_controller_ready_status
+Indication for a virt-controller that is ready to take the lead. Type: Gauge.
+
+### kubevirt_virt_controller_up
 The number of virt-controller pods that are up. Type: Gauge.
 
-### kubevirt_virt_handler_up_total
+### kubevirt_virt_handler_up
 The number of virt-handler pods that are up. Type: Gauge.
 
-### kubevirt_virt_operator_leading_total
+### kubevirt_virt_operator_leading
 The number of virt-operator pods that are leading. Type: Gauge.
 
-### kubevirt_virt_operator_ready_total
+### kubevirt_virt_operator_leading_status
+Indication for an operating virt-operator. Type: Gauge.
+
+### kubevirt_virt_operator_ready
 The number of virt-operator pods that are ready. Type: Gauge.
 
-### kubevirt_virt_operator_up_total
+### kubevirt_virt_operator_ready_status
+Indication for a virt-operator that is ready to take the lead. Type: Gauge.
+
+### kubevirt_virt_operator_up
 The number of virt-operator pods that are up. Type: Gauge.
 
 ### kubevirt_vm_container_free_memory_bytes_based_on_rss
@@ -114,7 +105,7 @@ Total CPU time spent in all modes (sum of both vcpu and hypervisor usage). Type:
 ### kubevirt_vmi_cpu_user_usage_seconds_total
 Total CPU time spent in user mode. Type: Counter.
 
-### kubevirt_vmi_filesystem_capacity_bytes_total
+### kubevirt_vmi_filesystem_capacity_bytes
 Total VM filesystem capacity in bytes. Type: Gauge.
 
 ### kubevirt_vmi_filesystem_used_bytes
@@ -129,22 +120,22 @@ Amount of usable memory as seen by the domain. This value may not be accurate if
 ### kubevirt_vmi_memory_cached_bytes
 The amount of memory that is being used to cache I/O and is available to be reclaimed, corresponds to the sum of `Buffers` + `Cached` + `SwapCached` in `/proc/meminfo`. Type: Gauge.
 
-### kubevirt_vmi_memory_domain_bytes_total
+### kubevirt_vmi_memory_domain_bytes
 The amount of memory in bytes allocated to the domain. The `memory` value in domain xml file. Type: Gauge.
 
-### kubevirt_vmi_memory_pgmajfault
+### kubevirt_vmi_memory_pgmajfault_total
 The number of page faults when disk IO was required. Page faults occur when a process makes a valid access to virtual memory that is not available. When servicing the page fault, if disk IO is required, it is considered as major fault. Type: Counter.
 
-### kubevirt_vmi_memory_pgminfault
+### kubevirt_vmi_memory_pgminfault_total
 The number of other page faults, when disk IO was not required. Page faults occur when a process makes a valid access to virtual memory that is not available. When servicing the page fault, if disk IO is NOT required, it is considered as minor fault. Type: Counter.
 
 ### kubevirt_vmi_memory_resident_bytes
 Resident set size of the process running the domain. Type: Gauge.
 
-### kubevirt_vmi_memory_swap_in_traffic_bytes_total
+### kubevirt_vmi_memory_swap_in_traffic_bytes
 The total amount of data read from swap space of the guest in bytes. Type: Gauge.
 
-### kubevirt_vmi_memory_swap_out_traffic_bytes_total
+### kubevirt_vmi_memory_swap_out_traffic_bytes
 The total amount of memory written out to swap space of the guest in bytes. Type: Gauge.
 
 ### kubevirt_vmi_memory_unused_bytes
@@ -159,6 +150,21 @@ Amount of `used` memory as seen by the domain. Type: Gauge.
 ### kubevirt_vmi_migration_phase_transition_time_from_creation_seconds
 Histogram of VM migration phase transitions duration from creation time in seconds. Type: Histogram.
 
+### kubevirt_vmi_migrations_failed
+Number of failed migrations. Type: Gauge.
+
+### kubevirt_vmi_migrations_pending
+Number of current pending migrations. Type: Gauge.
+
+### kubevirt_vmi_migrations_running
+Number of current running migrations. Type: Gauge.
+
+### kubevirt_vmi_migrations_scheduling
+Number of current scheduling migrations. Type: Gauge.
+
+### kubevirt_vmi_migrations_succeeded
+Number of migrations successfully executed. Type: Gauge.
+
 ### kubevirt_vmi_network_receive_bytes_total
 Total network traffic received in bytes. Type: Counter.
 
@@ -192,7 +198,7 @@ Number of VMI CPU affinities to node physical cores. Type: Gauge.
 ### kubevirt_vmi_non_evictable
 Indication for a VirtualMachine that its eviction strategy is set to Live Migration but is not migratable. Type: Gauge.
 
-### kubevirt_vmi_outdated_count
+### kubevirt_vmi_number_of_outdated
 Indication for the total number of VirtualMachineInstance workloads that are not running within the most up-to-date version of the virt-launcher environment. Type: Gauge.
 
 ### kubevirt_vmi_phase_count
@@ -210,42 +216,42 @@ Histogram of VM phase transitions duration between different phases in seconds.
 ### kubevirt_vmi_storage_flush_requests_total
 Total storage flush requests. Type: Counter.
 
-### kubevirt_vmi_storage_flush_times_ms_total
-Total time (ms) spent on cache flushing. Type: Counter.
+### kubevirt_vmi_storage_flush_times_seconds_total
+Total time spent on cache flushing. Type: Counter.
 
 ### kubevirt_vmi_storage_iops_read_total
 Total number of I/O read operations. Type: Counter.
 
 ### kubevirt_vmi_storage_iops_write_total
 Total number of I/O write operations. Type: Counter.
 
-### kubevirt_vmi_storage_read_times_ms_total
-Total time (ms) spent on read operations. Type: Counter.
+### kubevirt_vmi_storage_read_times_seconds_total
+Total time spent on read operations. Type: Counter.
 
 ### kubevirt_vmi_storage_read_traffic_bytes_total
 Total number of bytes read from storage. Type: Counter.
 
-### kubevirt_vmi_storage_write_times_ms_total
-Total time (ms) spent on write operations. Type: Counter.
+### kubevirt_vmi_storage_write_times_seconds_total
+Total time spent on write operations. Type: Counter.
 
 ### kubevirt_vmi_storage_write_traffic_bytes_total
 Total number of written bytes. Type: Counter.
 
 ### kubevirt_vmi_vcpu_delay_seconds_total
 Amount of time spent by each vcpu waiting in the queue instead of running. Type: Counter.
 
-### kubevirt_vmi_vcpu_seconds
+### kubevirt_vmi_vcpu_seconds_total
 Total amount of time spent in each state by each vcpu (cpu_time excluding hypervisor time). Where `id` is the vcpu identifier and `state` can be one of the following: [`OFFLINE`, `RUNNING`, `BLOCKED`]. Type: Counter.
 
-### kubevirt_vmi_vcpu_wait_seconds
+### kubevirt_vmi_vcpu_wait_seconds_total
 Amount of time spent by each vcpu while waiting on I/O. Type: Counter.
 
+### kubevirt_vmsnapshot_disks_restored_from_source
+Returns the total number of virtual machine disks restored from the source virtual machine. Type: Gauge.
+
 ### kubevirt_vmsnapshot_disks_restored_from_source_bytes
 Returns the amount of space in bytes restored from the source virtual machine. Type: Gauge.
 
-### kubevirt_vmsnapshot_disks_restored_from_source_total
-Returns the total number of virtual machine disks restored from the source virtual machine. Type: Gauge.
-
 ### kubevirt_vmsnapshot_persistentvolumeclaim_labels
 Returns the labels of the persistent volume claims that are used for restoring virtual machines. Type: Info.
 

diff --git a/hack/prom-rule-ci/prom-rules-tests.yaml b/hack/prom-rule-ci/prom-rules-tests.yaml
@@ -242,9 +242,9 @@ tests:
   # Some virt controllers are not ready
   - interval: 1m
     input_series:
-      - series: 'kubevirt_virt_controller_ready{namespace="ci", pod="virt-controller-1"}'
+      - series: 'kubevirt_virt_controller_ready_status{namespace="ci", pod="virt-controller-1"}'
         values: '1+0x11'
-      - series: 'kubevirt_virt_controller_ready{namespace="ci", pod="virt-controller-2"}'
+      - series: 'kubevirt_virt_controller_ready_status{namespace="ci", pod="virt-controller-2"}'
         values: '0+0x11'
       - series: 'up{namespace="ci", pod="virt-controller-1"}'
         values: '1+0x11'
@@ -267,7 +267,7 @@ tests:
   # All virt controllers are not ready
   - interval: 1m
     input_series:
-      - series: 'kubevirt_virt_controller_ready{namespace="ci", pod="virt-controller-1"}'
+      - series: 'kubevirt_virt_controller_ready_status{namespace="ci", pod="virt-controller-1"}'
         values: "0 0 0 0 0 0 0 0 0 0 0"
 
     alert_rule_test:
@@ -289,7 +289,7 @@ tests:
   # All virt controllers are not ready (ImagePullBackOff)
   - interval: 1m
     input_series:
-      - series: 'kubevirt_virt_controller_ready{namespace="ci", pod="virt-controller-1"}'
+      - series: 'kubevirt_virt_controller_ready_status{namespace="ci", pod="virt-controller-1"}'
         values: "stale stale stale stale stale stale stale stale stale stale"
 
     alert_rule_test:
@@ -312,7 +312,7 @@ tests:
   # All virt operators are not ready (ImagePullBackOff)
   - interval: 1m
     input_series:
-      - series: 'kubevirt_virt_operator_ready{namespace="ci", pod="virt-operator-1"}'
+      - series: 'kubevirt_virt_operator_ready_status{namespace="ci", pod="virt-operator-1"}'
         values: "stale stale stale stale stale stale stale stale stale stale"
 
     alert_rule_test:
@@ -335,7 +335,7 @@ tests:
   # All virt operators are not ready
   - interval: 1m
     input_series:
-      - series: 'kubevirt_virt_operator_ready{namespace="ci", pod="virt-operator-1"}'
+      - series: 'kubevirt_virt_operator_ready_status{namespace="ci", pod="virt-operator-1"}'
         values: "0 0 0 0 0 0 0 0 0 0 0"
 
     alert_rule_test:
@@ -725,7 +725,7 @@ tests:
   # Excessive VMI Migrations in a period of time
   - interval: 1h
     input_series:
-      - series: 'kubevirt_migrate_vmi_succeeded{vmi="vmi-example-1"}'
+      - series: 'kubevirt_vmi_migrations_succeeded{vmi="vmi-example-1"}'
         # time:  0 1 2 3 4 5
         values: "_ _ _ 1 7 13"
 

diff --git a/pkg/monitoring/domainstats/prometheus/prometheus.go b/pkg/monitoring/domainstats/prometheus/prometheus.go
@@ -161,7 +161,7 @@ func (metrics *vmiMetrics) updateMemory(mem *stats.DomainStatsMemory) {
 
 	if mem.SwapInSet {
 		metrics.pushCommonMetric(
-			"kubevirt_vmi_memory_swap_in_traffic_bytes_total",
+			"kubevirt_vmi_memory_swap_in_traffic_bytes",
 			"The total amount of data read from swap space of the guest in bytes.",
 			prometheus.GaugeValue,
 			float64(mem.SwapIn)*1024,
@@ -170,7 +170,7 @@ func (metrics *vmiMetrics) updateMemory(mem *stats.DomainStatsMemory) {
 
 	if mem.SwapOutSet {
 		metrics.pushCommonMetric(
-			"kubevirt_vmi_memory_swap_out_traffic_bytes_total",
+			"kubevirt_vmi_memory_swap_out_traffic_bytes",
 			"The total amount of memory written out to swap space of the guest in bytes.",
 			prometheus.GaugeValue,
 			float64(mem.SwapOut)*1024,
@@ -179,7 +179,7 @@ func (metrics *vmiMetrics) updateMemory(mem *stats.DomainStatsMemory) {
 
 	if mem.MajorFaultSet {
 		metrics.pushCommonMetric(
-			"kubevirt_vmi_memory_pgmajfault",
+			"kubevirt_vmi_memory_pgmajfault_total",
 			"The number of page faults when disk IO was required. Page faults occur when a process makes a valid access to virtual memory that is not available. When servicing the page fault, if disk IO is required, it is considered as major fault.",
 			prometheus.CounterValue,
 			float64(mem.MajorFault),
@@ -188,7 +188,7 @@ func (metrics *vmiMetrics) updateMemory(mem *stats.DomainStatsMemory) {
 
 	if mem.MinorFaultSet {
 		metrics.pushCommonMetric(
-			"kubevirt_vmi_memory_pgminfault",
+			"kubevirt_vmi_memory_pgminfault_total",
 			"The number of other page faults, when disk IO was not required. Page faults occur when a process makes a valid access to virtual memory that is not available. When servicing the page fault, if disk IO is NOT required, it is considered as minor fault.",
 			prometheus.CounterValue,
 			float64(mem.MinorFault),
@@ -215,7 +215,7 @@ func (metrics *vmiMetrics) updateMemory(mem *stats.DomainStatsMemory) {
 
 	if mem.TotalSet {
 		metrics.pushCommonMetric(
-			"kubevirt_vmi_memory_domain_bytes_total",
+			"kubevirt_vmi_memory_domain_bytes",
 			"The amount of memory in bytes allocated to the domain. The `memory` value in domain xml file.",
 			prometheus.GaugeValue,
 			float64(mem.Total)*1024,
@@ -285,7 +285,7 @@ func (metrics *vmiMetrics) updateVcpu(vcpuStats []stats.DomainStatsVcpu) {
 
 		if vcpu.StateSet && vcpu.TimeSet {
 			metrics.pushCustomMetric(
-				"kubevirt_vmi_vcpu_seconds",
+				"kubevirt_vmi_vcpu_seconds_total",
 				"Total amount of time spent in each state by each vcpu (cpu_time excluding hypervisor time). Where `id` is the vcpu identifier and `state` can be one of the following: [`OFFLINE`, `RUNNING`, `BLOCKED`].",
 				prometheus.CounterValue,
 				float64(vcpu.Time/1000000000),
@@ -296,10 +296,10 @@ func (metrics *vmiMetrics) updateVcpu(vcpuStats []stats.DomainStatsVcpu) {
 
 		if vcpu.WaitSet {
 			metrics.pushCustomMetric(
-				"kubevirt_vmi_vcpu_wait_seconds",
+				"kubevirt_vmi_vcpu_wait_seconds_total",
 				"Amount of time spent by each vcpu while waiting on I/O.",
 				prometheus.CounterValue,
-				float64(vcpu.Wait)/float64(1000000),
+				float64(vcpu.Wait)/float64(1000000000),
 				[]string{"id"},
 				[]string{stringVcpuIdx},
 			)
@@ -377,21 +377,21 @@ func (metrics *vmiMetrics) updateBlock(blkStats []stats.DomainStatsBlock) {
 
 		if block.RdTimesSet {
 			metrics.pushCustomMetric(
-				"kubevirt_vmi_storage_read_times_ms_total",
-				"Total time (ms) spent on read operations.",
+				"kubevirt_vmi_storage_read_times_seconds_total",
+				"Total time spent on read operations.",
 				prometheus.CounterValue,
-				float64(block.RdTimes)/1000000,
+				float64(block.RdTimes)/1000000000,
 				blkLabels,
 				blkLabelValues,
 			)
 		}
 
 		if block.WrTimesSet {
 			metrics.pushCustomMetric(
-				"kubevirt_vmi_storage_write_times_ms_total",
-				"Total time (ms) spent on write operations.",
+				"kubevirt_vmi_storage_write_times_seconds_total",
+				"Total time spent on write operations.",
 				prometheus.CounterValue,
-				float64(block.WrTimes)/1000000,
+				float64(block.WrTimes)/1000000000,
 				blkLabels,
 				blkLabelValues,
 			)
@@ -410,10 +410,10 @@ func (metrics *vmiMetrics) updateBlock(blkStats []stats.DomainStatsBlock) {
 
 		if block.FlTimesSet {
 			metrics.pushCustomMetric(
-				"kubevirt_vmi_storage_flush_times_ms_total",
-				"Total time (ms) spent on cache flushing.",
+				"kubevirt_vmi_storage_flush_times_seconds_total",
+				"Total time spent on cache flushing.",
 				prometheus.CounterValue,
-				float64(block.FlTimes)/1000000,
+				float64(block.FlTimes)/1000000000,
 				blkLabels,
 				blkLabelValues,
 			)
@@ -546,7 +546,7 @@ func (metrics *vmiMetrics) updateFilesystem(vmFSStats k6tv1.VirtualMachineInstan
 		fsLabelValues := []string{fsStat.DiskName, fsStat.MountPoint, fsStat.FileSystemType}
 
 		metrics.pushCustomMetric(
-			"kubevirt_vmi_filesystem_capacity_bytes_total",
+			"kubevirt_vmi_filesystem_capacity_bytes",
 			"Total VM filesystem capacity in bytes.",
 			prometheus.GaugeValue,
 			float64(fsStat.TotalBytes),