Skip to content

Commit

Permalink
add metrics.md document
Browse files Browse the repository at this point in the history
This change adds a document which details all the available metrics for
scraping by Prometheus. It has sample dumps along with some text to help
guide the reader.
  • Loading branch information
elmiko committed May 15, 2020
1 parent 09efe6c commit 4377d55
Showing 1 changed file with 190 additions and 0 deletions.
190 changes: 190 additions & 0 deletions docs/dev/metrics.md
@@ -0,0 +1,190 @@
# MAO Metrics

The Machine API Operator reports the following metrics:

Metrics about Machine resources managed by the operator:

```
# HELP mapi_machine_created_timestamp_seconds Timestamp of the mapi managed Machine creation time
# TYPE mapi_machine_created_timestamp_seconds gauge
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-master-0",namespace="openshift-machine-api",node="ip-10-0-130-139.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2a/i-08624d119917119d6"} 1.589550152e+09
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-master-1",namespace="openshift-machine-api",node="ip-10-0-148-9.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2b/i-09076ddde074d3fd1"} 1.589550152e+09
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-master-2",namespace="openshift-machine-api",node="ip-10-0-169-166.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2c/i-0587fa3c2530440d4"} 1.589550152e+09
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2a-v7ws4",namespace="openshift-machine-api",node="ip-10-0-139-181.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2a/i-0671fc268d3c14b8c"} 1.58955075e+09
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2b-4zcrl",namespace="openshift-machine-api",node="ip-10-0-157-190.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2b/i-04737ca3fa3d0e430"} 1.58955075e+09
mapi_machine_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2c-mfms8",namespace="openshift-machine-api",node="ip-10-0-164-212.us-east-2.compute.internal",phase="Running",spec_provider_id="aws:///us-east-2c/i-05e5346f8f5b27264"} 1.58955075e+09
# HELP mapi_machine_items Count of machine objects currently at the apiserver
# TYPE mapi_machine_items gauge
mapi_machine_items 6
```

Metrics about MachineSet resources managed by the operator:

```
# HELP mapi_machine_set_status_replicas Information of the mapi managed Machineset's status for replicas
# TYPE mapi_machine_set_status_replicas gauge
mapi_machine_set_status_replicas{name="ocp-cluster-rndpg-worker-us-east-2a",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas{name="ocp-cluster-rndpg-worker-us-east-2b",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas{name="ocp-cluster-rndpg-worker-us-east-2c",namespace="openshift-machine-api"} 1
# HELP mapi_machine_set_status_replicas_available Information of the mapi managed Machineset's status for available replicas
# TYPE mapi_machine_set_status_replicas_available gauge
mapi_machine_set_status_replicas_available{name="ocp-cluster-rndpg-worker-us-east-2a",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas_available{name="ocp-cluster-rndpg-worker-us-east-2b",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas_available{name="ocp-cluster-rndpg-worker-us-east-2c",namespace="openshift-machine-api"} 1
# HELP mapi_machine_set_status_replicas_ready Information of the mapi managed Machineset's status for ready replicas
# TYPE mapi_machine_set_status_replicas_ready gauge
mapi_machine_set_status_replicas_ready{name="ocp-cluster-rndpg-worker-us-east-2a",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas_ready{name="ocp-cluster-rndpg-worker-us-east-2b",namespace="openshift-machine-api"} 1
mapi_machine_set_status_replicas_ready{name="ocp-cluster-rndpg-worker-us-east-2c",namespace="openshift-machine-api"} 1
# HELP mapi_machineset_created_timestamp_seconds Timestamp of the mapi managed Machineset creation time
# TYPE mapi_machineset_created_timestamp_seconds gauge
mapi_machineset_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2a",namespace="openshift-machine-api"} 1.589550153e+09
mapi_machineset_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2b",namespace="openshift-machine-api"} 1.589550153e+09
mapi_machineset_created_timestamp_seconds{api_version="machine.openshift.io/v1beta1",name="ocp-cluster-rndpg-worker-us-east-2c",namespace="openshift-machine-api"} 1.589550153e+09
# HELP mapi_machineset_items Count of machinesets at the apiserver
# TYPE mapi_machineset_items gauge
mapi_machineset_items 3
```

Metrics about the resource collectors managed by the operator:

```
# HELP mapi_mao_collector_up Machine API Operator metrics are being collected and reported successfully
# TYPE mapi_mao_collector_up gauge
mapi_mao_collector_up{kind="mapi_machine_items"} 1
mapi_mao_collector_up{kind="mapi_machineset_items"} 1
```

Metrics about the internal state of the operator:

```
# HELP go_gc_duration_seconds A summary of the GC invocation durations.
# TYPE go_gc_duration_seconds summary
go_gc_duration_seconds{quantile="0"} 1.5703e-05
go_gc_duration_seconds{quantile="0.25"} 2.1954e-05
go_gc_duration_seconds{quantile="0.5"} 4.5334e-05
go_gc_duration_seconds{quantile="0.75"} 5.9324e-05
go_gc_duration_seconds{quantile="1"} 0.001408753
go_gc_duration_seconds_sum 0.006642518
go_gc_duration_seconds_count 92
# HELP go_goroutines Number of goroutines that currently exist.
# TYPE go_goroutines gauge
go_goroutines 56
# HELP go_memstats_alloc_bytes Number of bytes allocated and still in use.
# TYPE go_memstats_alloc_bytes gauge
go_memstats_alloc_bytes 9.273664e+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 2.03907472e+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 1.485642e+06
# HELP go_memstats_frees_total Total number of frees.
# TYPE go_memstats_frees_total counter
go_memstats_frees_total 1.285042e+06
# HELP go_memstats_gc_cpu_fraction The fraction of this program's available CPU time used by the GC since the program started.
# TYPE go_memstats_gc_cpu_fraction gauge
go_memstats_gc_cpu_fraction 1.4651583687884607e-05
# 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 2.459648e+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 9.273664e+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 5.2568064e+07
# 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 1.3492224e+07
# HELP go_memstats_heap_objects Number of allocated objects.
# TYPE go_memstats_heap_objects gauge
go_memstats_heap_objects 43744
# 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 5.1757056e+07
# 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 6.6060288e+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 1.5895610802562308e+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 1.328786e+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 6944
# 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 16384
# 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 149056
# 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 163840
# 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 1.692176e+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 1.117614e+06
# 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 983040
# 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 983040
# HELP go_memstats_sys_bytes Number of bytes obtained from system.
# TYPE go_memstats_sys_bytes gauge
go_memstats_sys_bytes 7.2286456e+07
# HELP go_threads Number of OS threads created.
# TYPE go_threads gauge
go_threads 11
# HELP process_cpu_seconds_total Total user and system CPU time spent in seconds.
# TYPE process_cpu_seconds_total counter
process_cpu_seconds_total 6.99
# 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 9
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 4.9967104e+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 1.58955072471e+09
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 1.48037632e+08
# 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
```

Metrics about the operator build environment:

```
# HELP go_info Information about the Go environment.
# TYPE go_info gauge
go_info{version="go1.13.4"} 1
```

Metrics about the Prometheus interface in the operator:

```
# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served.
# TYPE promhttp_metric_handler_requests_in_flight gauge
promhttp_metric_handler_requests_in_flight 1
# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code.
# TYPE promhttp_metric_handler_requests_total counter
promhttp_metric_handler_requests_total{code="200"} 648
promhttp_metric_handler_requests_total{code="500"} 0
promhttp_metric_handler_requests_total{code="503"} 0
```

0 comments on commit 4377d55

Please sign in to comment.