add health status tests

Author: mateuszdrab

docs/storage/prometheus.md

@@ -47,6 +47,7 @@ Metric name | Type | Description | Unit (where applicable) | option parameter |
 `container_fs_write_seconds_total` | Counter | Cumulative count of seconds spent writing | seconds | diskIO |
 `container_fs_writes_merged_total` | Counter | Cumulative count of writes merged | | diskIO |
 `container_fs_writes_total` | Counter | Cumulative count of writes completed | | diskIO |
+`container_health_state` | Gauge | State of the health check probe | | - |
 `container_hugetlb_failcnt` | Counter | Number of hugepage usage hits limits | | hugetlb |
 `container_hugetlb_max_usage_bytes` | Gauge | Maximum hugepage usages recorded | bytes | hugetlb |
 `container_hugetlb_usage_bytes` | Gauge | Current hugepage usage | bytes | hugetlb |

metrics/prometheus_fake.go

@@ -778,6 +778,7 @@ func (p testSubcontainersInfoProvider) GetRequestedContainersInfo(string, v2.Req
 						},
 					},
 					CpuSet: info.CPUSetStats{MemoryMigrate: 1},
+					Health: info.Health{Status: "healthy"},
 				},
 			},
 		},

metrics/prometheus_test.go

@@ -110,12 +110,13 @@ func TestPrometheusCollector_scrapeFailure(t *testing.T) {
 
 func TestNewPrometheusCollectorWithPerf(t *testing.T) {
 	c := NewPrometheusCollector(&mockInfoProvider{}, mockLabelFunc, container.MetricSet{container.PerfMetrics: struct{}{}}, now, v2.RequestOptions{})
-	assert.Len(t, c.containerMetrics, 5)
+	assert.Len(t, c.containerMetrics, 6)
 	names := []string{}
 	for _, m := range c.containerMetrics {
 		names = append(names, m.name)
 	}
 	assert.Contains(t, names, "container_last_seen")
+	assert.Contains(t, names, "container_health_state")
 	assert.Contains(t, names, "container_perf_events_total")
 	assert.Contains(t, names, "container_perf_events_scaling_ratio")
 	assert.Contains(t, names, "container_perf_uncore_events_total")

metrics/testdata/prometheus_metrics

@@ -124,6 +124,9 @@ container_fs_writes_merged_total{container_env_foo_env="prod",container_label_fo
 # TYPE container_fs_writes_total counter
 container_fs_writes_total{container_env_foo_env="prod",container_label_foo_label="bar",device="sda1",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 28 1395066363000
 container_fs_writes_total{container_env_foo_env="prod",container_label_foo_label="bar",device="sda2",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 43 1395066363000
+# HELP container_health_state The result of the container's health check
+# TYPE container_health_state gauge
+container_health_state{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 1 1395066363000
 # HELP container_hugetlb_failcnt Number of hugepage usage hits limits
 # TYPE container_hugetlb_failcnt counter
 container_hugetlb_failcnt{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",pagesize="1Gi",zone_name="hello"} 0 1395066363000

metrics/testdata/prometheus_metrics_perf_aggregated

@@ -1,6 +1,9 @@
 # HELP cadvisor_version_info A metric with a constant '1' value labeled by kernel version, OS version, docker version, cadvisor version & cadvisor revision.
 # TYPE cadvisor_version_info gauge
 cadvisor_version_info{cadvisorRevision="abcdef",cadvisorVersion="0.16.0",dockerVersion="1.8.1",kernelVersion="4.1.6-200.fc22.x86_64",osVersion="Fedora 22 (Twenty Two)"} 1
+# HELP container_health_state The result of the container's health check
+# TYPE container_health_state gauge
+container_health_state{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 1 1395066363000
 # HELP container_last_seen Last time a container was seen by the exporter
 # TYPE container_last_seen gauge
 container_last_seen{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 1.395066363e+09 1395066363000

metrics/testdata/prometheus_metrics_whitelist_filtered

@@ -124,6 +124,9 @@ container_fs_writes_merged_total{container_env_foo_env="prod",device="sda2",id="
 # TYPE container_fs_writes_total counter
 container_fs_writes_total{container_env_foo_env="prod",device="sda1",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 28 1395066363000
 container_fs_writes_total{container_env_foo_env="prod",device="sda2",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 43 1395066363000
+# HELP container_health_state The result of the container's health check
+# TYPE container_health_state gauge
+container_health_state{container_env_foo_env="prod",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 1 1395066363000
 # HELP container_hugetlb_failcnt Number of hugepage usage hits limits
 # TYPE container_hugetlb_failcnt counter
 container_hugetlb_failcnt{container_env_foo_env="prod",id="testcontainer",image="test",name="testcontaineralias",pagesize="1Gi",zone_name="hello"} 0 1395066363000