b6c7becbfe
This PR adds support for user-defined health-check probes for Docker
containers. It adds a `HEALTHCHECK` instruction to the Dockerfile syntax plus
some corresponding "docker run" options. It can be used with a restart policy
to automatically restart a container if the check fails.
The `HEALTHCHECK` instruction has two forms:
* `HEALTHCHECK [OPTIONS] CMD command` (check container health by running a command inside the container)
* `HEALTHCHECK NONE` (disable any healthcheck inherited from the base image)
The `HEALTHCHECK` instruction tells Docker how to test a container to check that
it is still working. This can detect cases such as a web server that is stuck in
an infinite loop and unable to handle new connections, even though the server
process is still running.
When a container has a healthcheck specified, it has a _health status_ in
addition to its normal status. This status is initially `starting`. Whenever a
health check passes, it becomes `healthy` (whatever state it was previously in).
After a certain number of consecutive failures, it becomes `unhealthy`.
The options that can appear before `CMD` are:
* `--interval=DURATION` (default: `30s`)
* `--timeout=DURATION` (default: `30s`)
* `--retries=N` (default: `1`)
The health check will first run **interval** seconds after the container is
started, and then again **interval** seconds after each previous check completes.
If a single run of the check takes longer than **timeout** seconds then the check
is considered to have failed.
It takes **retries** consecutive failures of the health check for the container
to be considered `unhealthy`.
There can only be one `HEALTHCHECK` instruction in a Dockerfile. If you list
more than one then only the last `HEALTHCHECK` will take effect.
The command after the `CMD` keyword can be either a shell command (e.g. `HEALTHCHECK
CMD /bin/check-running`) or an _exec_ array (as with other Dockerfile commands;
see e.g. `ENTRYPOINT` for details).
The command's exit status indicates the health status of the container.
The possible values are:
- 0: success - the container is healthy and ready for use
- 1: unhealthy - the container is not working correctly
- 2: starting - the container is not ready for use yet, but is working correctly
If the probe returns 2 ("starting") when the container has already moved out of the
"starting" state then it is treated as "unhealthy" instead.
For example, to check every five minutes or so that a web-server is able to
serve the site's main page within three seconds:
HEALTHCHECK --interval=5m --timeout=3s \
CMD curl -f http://localhost/ || exit 1
To help debug failing probes, any output text (UTF-8 encoded) that the command writes
on stdout or stderr will be stored in the health status and can be queried with
`docker inspect`. Such output should be kept short (only the first 4096 bytes
are stored currently).
When the health status of a container changes, a `health_status` event is
generated with the new status. The health status is also displayed in the
`docker ps` output.
Signed-off-by: Thomas Leonard <thomas.leonard@docker.com>
Signed-off-by: Sebastiaan van Stijn <github@gone.nl>
112 lines
2.9 KiB
Go
112 lines
2.9 KiB
Go
package daemon
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/docker/docker/container"
|
|
"github.com/docker/docker/daemon/events"
|
|
"github.com/docker/engine-api/types"
|
|
containertypes "github.com/docker/engine-api/types/container"
|
|
eventtypes "github.com/docker/engine-api/types/events"
|
|
)
|
|
|
|
func reset(c *container.Container) {
|
|
c.State = &container.State{}
|
|
c.State.Health = &container.Health{}
|
|
c.State.Health.Status = types.Starting
|
|
}
|
|
|
|
func TestHealthStates(t *testing.T) {
|
|
e := events.New()
|
|
_, l, _ := e.Subscribe()
|
|
defer e.Evict(l)
|
|
|
|
expect := func(expected string) {
|
|
select {
|
|
case event := <-l:
|
|
ev := event.(eventtypes.Message)
|
|
if ev.Status != expected {
|
|
t.Errorf("Expecting event %#v, but got %#v\n", expected, ev.Status)
|
|
}
|
|
case <-time.After(1 * time.Second):
|
|
t.Errorf("Expecting event %#v, but got nothing\n", expected)
|
|
}
|
|
}
|
|
|
|
c := &container.Container{
|
|
CommonContainer: container.CommonContainer{
|
|
ID: "container_id",
|
|
Name: "container_name",
|
|
Config: &containertypes.Config{
|
|
Image: "image_name",
|
|
},
|
|
},
|
|
}
|
|
daemon := &Daemon{
|
|
EventsService: e,
|
|
}
|
|
|
|
c.Config.Healthcheck = &containertypes.HealthConfig{
|
|
Retries: 1,
|
|
}
|
|
|
|
reset(c)
|
|
|
|
handleResult := func(startTime time.Time, exitCode int) {
|
|
handleProbeResult(daemon, c, &types.HealthcheckResult{
|
|
Start: startTime,
|
|
End: startTime,
|
|
ExitCode: exitCode,
|
|
})
|
|
}
|
|
|
|
// starting -> failed -> success -> failed
|
|
|
|
handleResult(c.State.StartedAt.Add(1*time.Second), 1)
|
|
expect("health_status: unhealthy")
|
|
|
|
handleResult(c.State.StartedAt.Add(2*time.Second), 0)
|
|
expect("health_status: healthy")
|
|
|
|
handleResult(c.State.StartedAt.Add(3*time.Second), 1)
|
|
expect("health_status: unhealthy")
|
|
|
|
// starting -> starting -> starting ->
|
|
// healthy -> starting (invalid transition)
|
|
|
|
reset(c)
|
|
|
|
handleResult(c.State.StartedAt.Add(20*time.Second), 2)
|
|
handleResult(c.State.StartedAt.Add(40*time.Second), 2)
|
|
if c.State.Health.Status != types.Starting {
|
|
t.Errorf("Expecting starting, but got %#v\n", c.State.Health.Status)
|
|
}
|
|
|
|
handleResult(c.State.StartedAt.Add(50*time.Second), 0)
|
|
expect("health_status: healthy")
|
|
handleResult(c.State.StartedAt.Add(60*time.Second), 2)
|
|
expect("health_status: unhealthy")
|
|
|
|
// Test retries
|
|
|
|
reset(c)
|
|
c.Config.Healthcheck.Retries = 3
|
|
|
|
handleResult(c.State.StartedAt.Add(20*time.Second), 1)
|
|
handleResult(c.State.StartedAt.Add(40*time.Second), 1)
|
|
if c.State.Health.Status != types.Starting {
|
|
t.Errorf("Expecting starting, but got %#v\n", c.State.Health.Status)
|
|
}
|
|
if c.State.Health.FailingStreak != 2 {
|
|
t.Errorf("Expecting FailingStreak=2, but got %d\n", c.State.Health.FailingStreak)
|
|
}
|
|
handleResult(c.State.StartedAt.Add(60*time.Second), 1)
|
|
expect("health_status: unhealthy")
|
|
|
|
handleResult(c.State.StartedAt.Add(80*time.Second), 0)
|
|
expect("health_status: healthy")
|
|
if c.State.Health.FailingStreak != 0 {
|
|
t.Errorf("Expecting FailingStreak=0, but got %d\n", c.State.Health.FailingStreak)
|
|
}
|
|
}
|