fix(server): Add read and write timeouts

There are a few documented scenarios where `kube-state-metrics` will
lock up(kubernetes#995, kubernetes#1028). I believe a much simpler solution to ensure
`kube-state-metrics` doesn't lock up and require a restart to server
`/metrics` requests is to add default read and write timeouts and to
allow them to be configurable. At Grafana, we've experienced a few
scenarios where `kube-state-metrics` running in larger clusters falls
behind and starts getting scraped multiple times. When this occurs,
`kube-state-metrics` becomes completely unresponsive and requires a
reboot. This is somewhat easily reproduceable(I'll provide a script in
an issue) and causes other critical workloads(KEDA, VPA) to fail in
weird ways.

Adds two flags:
- `server-read-timeout`
- `server-write-timeout`

Updates the metrics http server to set the `ReadTimeout` and
`WriteTimeout` to the configured values.

docs/developer/cli-arguments.md

@@ -67,6 +67,8 @@ Flags:
       --pod-namespace string                       Name of the namespace of the pod specified by --pod. When set, it is expected that --pod and --pod-namespace are both set. Most likely this should be passed via the downward API. This is used for auto-detecting sharding. If set, this has preference over statically configured sharding. This is experimental, it may be removed without notice.
       --port int                                   Port to expose metrics on. (default 8080)
       --resources string                           Comma-separated list of Resources to be enabled. Defaults to "certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments"
+      --server-read-timeout duration               The maximum duration for reading the entire request, including the body. (default 30s)
+      --server-write-timeout duration              The maximum duration before timing out writes of the response. (default 1m0s)
       --shard int32                                The instances shard nominal (zero indexed) within the total number of shards. (default 0)
       --skip_headers                               If true, avoid header prefixes in the log messages
       --skip_log_headers                           If true, avoid headers when opening log files (no effect when -logtostderr=true)

pkg/app/server.go

@@ -326,6 +326,8 @@ func RunKubeStateMetrics(ctx context.Context, opts *options.Options) error {
 	metricsServer := http.Server{
 		Handler:           metricsMux,
 		ReadHeaderTimeout: 5 * time.Second,
+		ReadTimeout:       opts.ServerReadTimeout,
+		WriteTimeout:      opts.ServerWriteTimeout,
 	}
 	metricsFlags := web.FlagConfig{
 		WebListenAddresses: &[]string{metricsServerListenAddress},
@@ -401,7 +403,6 @@ func buildMetricsServer(m *metricshandler.MetricsHandler, durationObserver prome
 	mux.Handle("/debug/pprof/trace", http.HandlerFunc(pprof.Trace))
 
 	mux.Handle(metricsPath, promhttp.InstrumentHandlerDuration(durationObserver, m))
-
 	// Add healthzPath
 	mux.HandleFunc(healthzPath, func(w http.ResponseWriter, _ *http.Request) {
 		w.WriteHeader(http.StatusOK)

pkg/options/options.go

@@ -21,6 +21,7 @@ import (
 	"fmt"
 	"os"
 	"strings"
+	"time"
 
 	"github.com/prometheus/common/version"
 	"github.com/spf13/cobra"
@@ -55,6 +56,8 @@ type Options struct {
 	TelemetryPort            int             `yaml:"telemetry_port"`
 	TotalShards              int             `yaml:"total_shards"`
 	UseAPIServerCache        bool            `yaml:"use_api_server_cache"`
+	ServerReadTimeout        time.Duration   `yaml:"server_read_timeout"`
+	ServerWriteTimeout       time.Duration   `yaml:"server_write_timeout"`
 
 	Config string
 
@@ -146,6 +149,8 @@ func (o *Options) AddFlags(cmd *cobra.Command) {
 	o.cmd.Flags().Var(&o.Namespaces, "namespaces", fmt.Sprintf("Comma-separated list of namespaces to be enabled. Defaults to %q", &DefaultNamespaces))
 	o.cmd.Flags().Var(&o.NamespacesDenylist, "namespaces-denylist", "Comma-separated list of namespaces not to be enabled. If namespaces and namespaces-denylist are both set, only namespaces that are excluded in namespaces-denylist will be used.")
 	o.cmd.Flags().Var(&o.Resources, "resources", fmt.Sprintf("Comma-separated list of Resources to be enabled. Defaults to %q", &DefaultResources))
+	o.cmd.Flags().DurationVar(&o.ServerReadTimeout, "server-read-timeout", 30*time.Second, "The maximum duration for reading the entire request, including the body.")
+	o.cmd.Flags().DurationVar(&o.ServerWriteTimeout, "server-write-timeout", 60*time.Second, "The maximum duration before timing out writes of the response.")
 }
 
 // Parse parses the flag definitions from the argument list.