Use a timeout for docker list & stat cmds

closes #1133

CHANGELOG.md

@@ -88,6 +88,8 @@ based on _prefix_ in addition to globs. This means that a filter like
 - [#1125](https://github.com/influxdata/telegraf/pull/1125): Wrap all exec command runners with a timeout, so hung os processes don't halt Telegraf.
 - [#1113](https://github.com/influxdata/telegraf/pull/1113): Set MaxRetry and RequiredAcks defaults in Kafka output.
 - [#1090](https://github.com/influxdata/telegraf/issues/1090): [agent] and [global_tags] config sometimes not getting applied.
+- [#1133](https://github.com/influxdata/telegraf/issues/1133): Use a timeout for docker list & stat cmds.
+- [#1052](https://github.com/influxdata/telegraf/issues/1052): Docker panic fix when decode fails.
 
 ## v0.12.1 [2016-04-14]
 

etc/telegraf.conf

@@ -565,6 +565,8 @@
 #   endpoint = "unix:///var/run/docker.sock"
 #   ## Only collect metrics for these containers, collect all if empty
 #   container_names = []
+#   ## Timeout for docker list, info, and stats commands
+#   timeout = "5s"
 
 
 # # Read statistics from one or many dovecot servers
@@ -600,6 +602,9 @@
 #   ## Commands array
 #   commands = ["/tmp/test.sh", "/usr/bin/mycollector --foo=bar"]
 # 
+#   ## Timeout for each command to complete.
+#   timeout = "5s"
+# 
 #   ## measurement name suffix (for separating different commands)
 #   name_suffix = "_mycollector"
 # 

plugins/inputs/docker/docker.go

@@ -16,6 +16,7 @@ import (
 	"github.com/docker/engine-api/client"
 	"github.com/docker/engine-api/types"
 	"github.com/influxdata/telegraf"
+	"github.com/influxdata/telegraf/internal"
 	"github.com/influxdata/telegraf/plugins/inputs"
 )
 
@@ -23,6 +24,7 @@ import (
 type Docker struct {
 	Endpoint       string
 	ContainerNames []string
+	Timeout        internal.Duration
 
 	client DockerClient
 }
@@ -54,6 +56,8 @@ var sampleConfig = `
   endpoint = "unix:///var/run/docker.sock"
   ## Only collect metrics for these containers, collect all if empty
   container_names = []
+  ## Timeout for docker list, info, and stats commands
+  timeout = "5s"
 `
 
 // Description returns input description
@@ -97,7 +101,9 @@ func (d *Docker) Gather(acc telegraf.Accumulator) error {
 
 	// List containers
 	opts := types.ContainerListOptions{}
-	containers, err := d.client.ContainerList(context.Background(), opts)
+	ctx, cancel := context.WithTimeout(context.Background(), d.Timeout.Duration)
+	defer cancel()
+	containers, err := d.client.ContainerList(ctx, opts)
 	if err != nil {
 		return err
 	}
@@ -106,7 +112,6 @@ func (d *Docker) Gather(acc telegraf.Accumulator) error {
 	var wg sync.WaitGroup
 	wg.Add(len(containers))
 	for _, container := range containers {
-
 		go func(c types.Container) {
 			defer wg.Done()
 			err := d.gatherContainer(c, acc)
@@ -127,7 +132,9 @@ func (d *Docker) gatherInfo(acc telegraf.Accumulator) error {
 	metadataFields := make(map[string]interface{})
 	now := time.Now()
 	// Get info from docker daemon
-	info, err := d.client.Info(context.Background())
+	ctx, cancel := context.WithTimeout(context.Background(), d.Timeout.Duration)
+	defer cancel()
+	info, err := d.client.Info(ctx)
 	if err != nil {
 		return err
 	}
@@ -210,7 +217,9 @@ func (d *Docker) gatherContainer(
 		}
 	}
 
-	r, err := d.client.ContainerStats(context.Background(), container.ID, false)
+	ctx, cancel := context.WithTimeout(context.Background(), d.Timeout.Duration)
+	defer cancel()
+	r, err := d.client.ContainerStats(ctx, container.ID, false)
 	if err != nil {
 		log.Printf("Error getting docker stats: %s\n", err.Error())
 	}