Metrics for the SCONE Service Operator

Retrieve the metrics from the metrics service endpoint

You can retrieve the metrics published by the scone-service-operator with the following commands.

Create a port-forward to the metrics service endpoint.

export SCONE_SERVICE_OPERATOR_NAMESPACE=osc-sec-scone-svc-operator
k port-forward -n $SCONE_SERVICE_OPERATOR_NAMESPACE service/scone-service-operator-controller-metrics 8080:8080

From another terminal, run the following command to retrieve the metrics:

curl http://localhost:8080/metrics

Scone Service Operator Metrics

# HELP certwatcher_read_certificate_errors_total Total number of certificate read errors
# TYPE certwatcher_read_certificate_errors_total counter
certwatcher_read_certificate_errors_total 0
# HELP certwatcher_read_certificate_total Total number of certificate reads
# TYPE certwatcher_read_certificate_total counter
certwatcher_read_certificate_total 1
# HELP controller_runtime_active_workers Number of currently used workers per controller
# TYPE controller_runtime_active_workers gauge
controller_runtime_active_workers{controller="scone"} 0
# HELP controller_runtime_max_concurrent_reconciles Maximum number of concurrent reconciles per controller
# TYPE controller_runtime_max_concurrent_reconciles gauge
controller_runtime_max_concurrent_reconciles{controller="scone"} 1
# HELP controller_runtime_reconcile_errors_total Total number of reconciliation errors per controller
# TYPE controller_runtime_reconcile_errors_total counter
controller_runtime_reconcile_errors_total{controller="scone"} 0
# HELP controller_runtime_reconcile_total Total number of reconciliations per controller
# TYPE controller_runtime_reconcile_total counter
controller_runtime_reconcile_total{controller="scone",result="error"} 0
controller_runtime_reconcile_total{controller="scone",result="requeue"} 0
controller_runtime_reconcile_total{controller="scone",result="requeue_after"} 0
controller_runtime_reconcile_total{controller="scone",result="success"} 0
# HELP controller_runtime_webhook_requests_in_flight Current number of admission requests being served.
# TYPE controller_runtime_webhook_requests_in_flight gauge
controller_runtime_webhook_requests_in_flight{webhook="/mutate-services-scone-cloud-v1beta1-cas"} 0
controller_runtime_webhook_requests_in_flight{webhook="/validate-confidential-security-osc-t-systems-com-v1alpha1-scone"} 0
controller_runtime_webhook_requests_in_flight{webhook="/validate-services-scone-cloud-v1beta1-cas"} 0
# HELP controller_runtime_webhook_requests_total Total number of admission requests by HTTP status code.
# TYPE controller_runtime_webhook_requests_total counter
controller_runtime_webhook_requests_total{code="200",webhook="/mutate-services-scone-cloud-v1beta1-cas"} 0
controller_runtime_webhook_requests_total{code="200",webhook="/validate-confidential-security-osc-t-systems-com-v1alpha1-scone"} 0
controller_runtime_webhook_requests_total{code="200",webhook="/validate-services-scone-cloud-v1beta1-cas"} 0
controller_runtime_webhook_requests_total{code="500",webhook="/mutate-services-scone-cloud-v1beta1-cas"} 0
controller_runtime_webhook_requests_total{code="500",webhook="/validate-confidential-security-osc-t-systems-com-v1alpha1-scone"} 0
controller_runtime_webhook_requests_total{code="500",webhook="/validate-services-scone-cloud-v1beta1-cas"} 0
# HELP go_gc_duration_seconds A summary of the pause duration of garbage collection cycles.
# TYPE go_gc_duration_seconds summary
go_gc_duration_seconds{quantile="0"} 3.3998e-05
go_gc_duration_seconds{quantile="0.25"} 3.9339e-05
go_gc_duration_seconds{quantile="0.5"} 4.4502e-05
go_gc_duration_seconds{quantile="0.75"} 7.5572e-05
go_gc_duration_seconds{quantile="1"} 0.000345838
go_gc_duration_seconds_sum 0.010850869
go_gc_duration_seconds_count 167
# HELP go_goroutines Number of goroutines that currently exist.
# TYPE go_goroutines gauge
go_goroutines 47
# HELP go_info Information about the Go environment.
# TYPE go_info gauge
go_info{version="go1.22.4"} 1
# HELP go_memstats_alloc_bytes Number of bytes allocated and still in use.
# TYPE go_memstats_alloc_bytes gauge
go_memstats_alloc_bytes 7.917472e+06
# HELP go_memstats_alloc_bytes_total Total number of bytes allocated, even if freed.
# TYPE go_memstats_alloc_bytes_total counter
go_memstats_alloc_bytes_total 5.8358292e+08
# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table.
# TYPE go_memstats_buck_hash_sys_bytes gauge
go_memstats_buck_hash_sys_bytes 1.536884e+06
# HELP go_memstats_frees_total Total number of frees.
# TYPE go_memstats_frees_total counter
go_memstats_frees_total 3.941242e+06
# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata.
# TYPE go_memstats_gc_sys_bytes gauge
go_memstats_gc_sys_bytes 3.463544e+06
# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and still in use.
# TYPE go_memstats_heap_alloc_bytes gauge
go_memstats_heap_alloc_bytes 7.917472e+06
# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used.
# TYPE go_memstats_heap_idle_bytes gauge
go_memstats_heap_idle_bytes 8.290304e+06
# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use.
# TYPE go_memstats_heap_inuse_bytes gauge
go_memstats_heap_inuse_bytes 1.1288576e+07
# HELP go_memstats_heap_objects Number of allocated objects.
# TYPE go_memstats_heap_objects gauge
go_memstats_heap_objects 25021
# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS.
# TYPE go_memstats_heap_released_bytes gauge
go_memstats_heap_released_bytes 7.462912e+06
# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system.
# TYPE go_memstats_heap_sys_bytes gauge
go_memstats_heap_sys_bytes 1.957888e+07
# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection.
# TYPE go_memstats_last_gc_time_seconds gauge
go_memstats_last_gc_time_seconds 1.7260601083890316e+09
# HELP go_memstats_lookups_total Total number of pointer lookups.
# TYPE go_memstats_lookups_total counter
go_memstats_lookups_total 0
# HELP go_memstats_mallocs_total Total number of mallocs.
# TYPE go_memstats_mallocs_total counter
go_memstats_mallocs_total 3.966263e+06
# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures.
# TYPE go_memstats_mcache_inuse_bytes gauge
go_memstats_mcache_inuse_bytes 4800
# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system.
# TYPE go_memstats_mcache_sys_bytes gauge
go_memstats_mcache_sys_bytes 15600
# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures.
# TYPE go_memstats_mspan_inuse_bytes gauge
go_memstats_mspan_inuse_bytes 167520
# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system.
# TYPE go_memstats_mspan_sys_bytes gauge
go_memstats_mspan_sys_bytes 195840
# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place.
# TYPE go_memstats_next_gc_bytes gauge
go_memstats_next_gc_bytes 1.3738968e+07
# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations.
# TYPE go_memstats_other_sys_bytes gauge
go_memstats_other_sys_bytes 953900
# HELP go_memstats_stack_inuse_bytes Number of bytes in use by the stack allocator.
# TYPE go_memstats_stack_inuse_bytes gauge
go_memstats_stack_inuse_bytes 1.343488e+06
# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator.
# TYPE go_memstats_stack_sys_bytes gauge
go_memstats_stack_sys_bytes 1.343488e+06
# HELP go_memstats_sys_bytes Number of bytes obtained from system.
# TYPE go_memstats_sys_bytes gauge
go_memstats_sys_bytes 2.7088136e+07
# HELP go_threads Number of OS threads created.
# TYPE go_threads gauge
go_threads 10
# HELP leader_election_master_status Gauge of if the reporting system is master of the relevant lease, 0 indicates backup, 1 indicates master. 'name' is the string used to identify the lease. Please make sure to group by name.
# TYPE leader_election_master_status gauge
leader_election_master_status{name="scone-service-operator.confidential.security.osc.t-systems.com"} 1
# HELP osc_sec_scone_billing_cpu_count The total number of CPUs relevant for billing
# TYPE osc_sec_scone_billing_cpu_count gauge
osc_sec_scone_billing_cpu_count{name="Billing LAS CPU count"} 0
# HELP osc_sws_disabled_safeguards Indicates whether the CR has disabled safeguards
# TYPE osc_sws_disabled_safeguards gauge
osc_sws_disabled_safeguards{cr_name="scone",cr_namespace="",cr_type="Scone",safeguard_name="unmanaged"} 0
# HELP osc_sws_operator_safe_to_delete Indicates whether the operator is safe to delete
# TYPE osc_sws_operator_safe_to_delete gauge
osc_sws_operator_safe_to_delete{operator_name="osc-sec-scone-controller"} 1
# HELP osc_sws_total_cr_count The total number of CRs of the given type
# TYPE osc_sws_total_cr_count gauge
osc_sws_total_cr_count{cr_type="Scone",operator_name="osc-sec-scone-controller"} 0
# HELP process_cpu_seconds_total Total user and system CPU time spent in seconds.
# TYPE process_cpu_seconds_total counter
process_cpu_seconds_total 17.39
# HELP process_max_fds Maximum number of open file descriptors.
# TYPE process_max_fds gauge
process_max_fds 1.048576e+06
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 14
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 5.474304e+07
# HELP process_start_time_seconds Start time of the process since unix epoch in seconds.
# TYPE process_start_time_seconds gauge
process_start_time_seconds 1.72604054825e+09
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 5.605801984e+09
# HELP process_virtual_memory_max_bytes Maximum amount of virtual memory available in bytes.
# TYPE process_virtual_memory_max_bytes gauge
process_virtual_memory_max_bytes 1.8446744073709552e+19
# HELP rest_client_requests_total Number of HTTP requests, partitioned by status code, method, and host.
# TYPE rest_client_requests_total counter
rest_client_requests_total{code="200",host="api.vk01.sec.internal.fgd1.ffm-dev.osc:443",method="GET"} 54
rest_client_requests_total{code="200",host="api.vk01.sec.internal.fgd1.ffm-dev.osc:443",method="PUT"} 9770
rest_client_requests_total{code="201",host="api.vk01.sec.internal.fgd1.ffm-dev.osc:443",method="POST"} 1
rest_client_requests_total{code="404",host="api.vk01.sec.internal.fgd1.ffm-dev.osc:443",method="GET"} 326
# HELP workqueue_adds_total Total number of adds handled by workqueue
# TYPE workqueue_adds_total counter
workqueue_adds_total{name="scone"} 0
# HELP workqueue_depth Current depth of workqueue
# TYPE workqueue_depth gauge
workqueue_depth{name="scone"} 0
# HELP workqueue_longest_running_processor_seconds How many seconds has the longest running processor for workqueue been running.
# TYPE workqueue_longest_running_processor_seconds gauge
workqueue_longest_running_processor_seconds{name="scone"} 0
# HELP workqueue_queue_duration_seconds How long in seconds an item stays in workqueue before being requested
# TYPE workqueue_queue_duration_seconds histogram
workqueue_queue_duration_seconds_bucket{name="scone",le="1e-08"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="1e-07"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="1e-06"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="9.999999999999999e-06"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="9.999999999999999e-05"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="0.001"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="0.01"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="0.1"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="1"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="10"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="100"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="1000"} 0
workqueue_queue_duration_seconds_bucket{name="scone",le="+Inf"} 0
workqueue_queue_duration_seconds_sum{name="scone"} 0
workqueue_queue_duration_seconds_count{name="scone"} 0
# HELP workqueue_retries_total Total number of retries handled by workqueue
# TYPE workqueue_retries_total counter
workqueue_retries_total{name="scone"} 0
# HELP workqueue_unfinished_work_seconds How many seconds of work has been done that is in progress and hasn't been observed by work_duration. Large values indicate stuck threads. One can deduce the number of stuck threads by observing the rate at which this increases.
# TYPE workqueue_unfinished_work_seconds gauge
workqueue_unfinished_work_seconds{name="scone"} 0
# HELP workqueue_work_duration_seconds How long in seconds processing an item from workqueue takes.
# TYPE workqueue_work_duration_seconds histogram
workqueue_work_duration_seconds_bucket{name="scone",le="1e-08"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="1e-07"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="1e-06"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="9.999999999999999e-06"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="9.999999999999999e-05"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="0.001"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="0.01"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="0.1"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="1"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="10"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="100"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="1000"} 0
workqueue_work_duration_seconds_bucket{name="scone",le="+Inf"} 0
workqueue_work_duration_seconds_sum{name="scone"} 0
workqueue_work_duration_seconds_count{name="scone"} 0