PLT-4357 adding performance monitoring (#4622)

* WIP

* WIP

* Adding metrics collection

* updating vendor packages

* Adding metrics to config

* Adding admin console page for perf monitoring

* Updating glide

* switching to tylerb/graceful

1 files changed, 118 insertions, 0 deletions

diff --git a/vendor/github.com/prometheus/client_golang/prometheus/example_clustermanager_test.go b/vendor/github.com/prometheus/client_golang/prometheus/example_clustermanager_test.go
new file mode 100644
index 000000000..260c1b52d
--- /dev/null
+++ b/vendor/github.com/prometheus/client_golang/prometheus/example_clustermanager_test.go
@@ -0,0 +1,118 @@
+// Copyright 2014 The Prometheus Authors
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+package prometheus_test
+
+import "github.com/prometheus/client_golang/prometheus"
+
+// ClusterManager is an example for a system that might have been built without
+// Prometheus in mind. It models a central manager of jobs running in a
+// cluster. To turn it into something that collects Prometheus metrics, we
+// simply add the two methods required for the Collector interface.
+//
+// An additional challenge is that multiple instances of the ClusterManager are
+// run within the same binary, each in charge of a different zone. We need to
+// make use of ConstLabels to be able to register each ClusterManager instance
+// with Prometheus.
+type ClusterManager struct {
+	Zone         string
+	OOMCountDesc *prometheus.Desc
+	RAMUsageDesc *prometheus.Desc
+	// ... many more fields
+}
+
+// ReallyExpensiveAssessmentOfTheSystemState is a mock for the data gathering a
+// real cluster manager would have to do. Since it may actually be really
+// expensive, it must only be called once per collection. This implementation,
+// obviously, only returns some made-up data.
+func (c *ClusterManager) ReallyExpensiveAssessmentOfTheSystemState() (
+	oomCountByHost map[string]int, ramUsageByHost map[string]float64,
+) {
+	// Just example fake data.
+	oomCountByHost = map[string]int{
+		"foo.example.org": 42,
+		"bar.example.org": 2001,
+	}
+	ramUsageByHost = map[string]float64{
+		"foo.example.org": 6.023e23,
+		"bar.example.org": 3.14,
+	}
+	return
+}
+
+// Describe simply sends the two Descs in the struct to the channel.
+func (c *ClusterManager) Describe(ch chan<- *prometheus.Desc) {
+	ch <- c.OOMCountDesc
+	ch <- c.RAMUsageDesc
+}
+
+// Collect first triggers the ReallyExpensiveAssessmentOfTheSystemState. Then it
+// creates constant metrics for each host on the fly based on the returned data.
+//
+// Note that Collect could be called concurrently, so we depend on
+// ReallyExpensiveAssessmentOfTheSystemState to be concurrency-safe.
+func (c *ClusterManager) Collect(ch chan<- prometheus.Metric) {
+	oomCountByHost, ramUsageByHost := c.ReallyExpensiveAssessmentOfTheSystemState()
+	for host, oomCount := range oomCountByHost {
+		ch <- prometheus.MustNewConstMetric(
+			c.OOMCountDesc,
+			prometheus.CounterValue,
+			float64(oomCount),
+			host,
+		)
+	}
+	for host, ramUsage := range ramUsageByHost {
+		ch <- prometheus.MustNewConstMetric(
+			c.RAMUsageDesc,
+			prometheus.GaugeValue,
+			ramUsage,
+			host,
+		)
+	}
+}
+
+// NewClusterManager creates the two Descs OOMCountDesc and RAMUsageDesc. Note
+// that the zone is set as a ConstLabel. (It's different in each instance of the
+// ClusterManager, but constant over the lifetime of an instance.) Then there is
+// a variable label "host", since we want to partition the collected metrics by
+// host. Since all Descs created in this way are consistent across instances,
+// with a guaranteed distinction by the "zone" label, we can register different
+// ClusterManager instances with the same registry.
+func NewClusterManager(zone string) *ClusterManager {
+	return &ClusterManager{
+		Zone: zone,
+		OOMCountDesc: prometheus.NewDesc(
+			"clustermanager_oom_crashes_total",
+			"Number of OOM crashes.",
+			[]string{"host"},
+			prometheus.Labels{"zone": zone},
+		),
+		RAMUsageDesc: prometheus.NewDesc(
+			"clustermanager_ram_usage_bytes",
+			"RAM usage as reported to the cluster manager.",
+			[]string{"host"},
+			prometheus.Labels{"zone": zone},
+		),
+	}
+}
+
+func ExampleCollector() {
+	workerDB := NewClusterManager("db")
+	workerCA := NewClusterManager("ca")
+
+	// Since we are dealing with custom Collector implementations, it might
+	// be a good idea to try it out with a pedantic registry.
+	reg := prometheus.NewPedanticRegistry()
+	reg.MustRegister(workerDB)
+	reg.MustRegister(workerCA)
+}